AI provider setup
Pick an AI provider (Anthropic, OpenAI, Groq, xAI, OpenRouter, z.ai) and paste your API key. Mediator never charges you — you pay the provider.
Mediator uses whichever AI provider you point it at. There's no shared account, no proxy — the API key you paste here is what your mediators use to generate replies. That has two consequences:
- You control the cost. Look at your provider's dashboard for spending; if Mediator's usage matters, you'll see it there directly.
- You control the model. Once the key is saved, you can fetch the list of models and pick one for your account. That model powers every mediator; the AI Assistant on the Settings page can use the same one or a different one.
Choosing a provider
- Anthropic (Claude) — best for nuanced dialogue and instruction-following. Recommended if you have an Anthropic API key.
- OpenAI (GPT-4o family, o1, o3) — the most familiar option. Works, but be aware OpenAI's
/v1/modelsreturns dozens of non-chat models (embeddings, TTS, image, etc.) mixed with chat models; Mediator filters those out automatically. - Groq — extremely fast inference on open-weight models (Llama, DeepSeek, Mixtral). Best pick if latency matters.
- xAI (Grok) — self-explanatory; works fine.
- OpenRouter — proxy to multiple models from many labs. Useful for trying niche models without signing up per-provider.
- z.ai — GLM family.
How the key is stored
The key is encrypted at rest with the app's ENCRYPTION_KEY. It never appears in logs. The settings page shows a preview of the currently-saved key so you can tell which one is active without exposing the whole thing.
Model catalog
Every model each provider offers, with capabilities, context/output limits, modalities and per-1M-token pricing. Drawn from the public models.dev registry — no API key needed. Use it to compare models before you pick one.
Anthropic (Claude) 17
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| Claude Fable 5claude-fable-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Released: 2026-06-07Last updated: 2026-06-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude model for creative writing, analysis, and controlled agent workflows [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Claude Fable 5.1claude-fable-5-1 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $0.25Cache write: 💵 $12.50 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude model for demanding reasoning and long-horizon agentic work [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
Claude Opus 4.5
| Context window: 200,000Output limit: 64,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2025-05Released: 2025-11-24Last updated:
| 💬🖼️🔧🧠📋🔊📎🌡️ Flagship Claude model for deep reasoning, coding, and long-horizon agents [{"type": "effort", "values": ["low", "medium", "high"]}, {"type": "budget_tokens", "min": 1024}] |
| Claude Opus 4.6claude-opus-4-6 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2025-05-31Released: 2026-02-04Last updated: 2026-03-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ High-end Claude for difficult coding, planning, and slower expert reasoning [{"type": "effort", "values": ["low", "medium", "high", "max"]}, {"type": "budget_tokens", "min": 1024}] |
| Claude Opus 4.7claude-opus-4-7 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-01-31Released: 2026-04-14Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Stronger Opus tier for advanced software work and high-stakes reasoning [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Claude Opus 4.8claude-opus-4-8 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-01Released, Last updated: 2026-05-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Claude Opus 5claude-opus-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-05Released, Last updated: 2026-07-24Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Strongest Claude Opus model for coding, agents, and professional work [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Claude Opus 5.5claude-opus-5-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.20Cache write: 💵 $5.00 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude model for long-running agentic coding and knowledge work [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
Claude Sonnet 4.5
| Context window: 200,000Output limit: 64,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00Cache read: 💵 $0.30Cache write: 💵 $3.75 | Knowledge cutoff: 2025-07-31Released: 2025-09-29Last updated: 2025-09-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Balanced Claude model for coding, analysis, agent workflows, and cost control [{"type": "budget_tokens", "min": 1024}] |
| Claude Sonnet 4.6claude-sonnet-4-6 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00Cache read: 💵 $0.30Cache write: 💵 $3.75 | Knowledge cutoff: 2025-08-31Released: 2026-02-17Last updated: 2026-03-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude workhorse for coding agents, careful analysis, and production cost control [{"type": "effort", "values": ["low", "medium", "high", "max"]}, {"type": "budget_tokens", "min": 1024}] |
| Claude Sonnet 5claude-sonnet-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-01-31Released: 2026-06-29Last updated: 2026-06-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Everyday Claude agent model for coding, planning, browsing, and general work [{"type": "toggle"}, {"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Claude Sonnet 5.5claude-sonnet-5-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast Claude model for everyday coding, agents, and knowledge work [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
Claude Haiku 4.5
| Context window: 200,000Output limit: 64,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.10Cache write: 💵 $1.25 | Knowledge cutoff: 2025-02-28Released: 2025-10-15Last updated: 2025-10-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast Claude lane for lightweight agents, office tasks, and responsive chat [{"type": "budget_tokens", "min": 1024}] |
| Claude Haiku 5.5claude-haiku-5-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Knowledge cutoff: 2026-06Released, Last updated: 2026-10-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast Claude model for responsive assistance, classification, and lightweight agents [{"type": "toggle"}, {"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
Groq 12
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| Qwen3.8 27Bqwen/qwen3.8-27b | Context window: 131,072Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.80Output: 💵 $4.00 | Released, Last updated: 2026-08-14Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Dense 27B vision-language model for coding, agent tasks, and image and video understanding [{"type": "effort", "values": ["none", "default", "low", "medium", "high"]}] |
| Qwen3.6 27Bqwen/qwen3.6-27b | Context window: 131,072Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.60Output: 💵 $3.00Cache read: 💵 $0.30 | Released, Last updated: 2026-04-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen vision-language model for visual reasoning, documents, and agent tasks [{"type": "effort", "values": ["none", "default"]}] |
| Llama 3.3 70Bllama-3.3-70b-versatile | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.59Output: 💵 $0.79 | Knowledge cutoff: 2023-12Released, Last updated: 2024-12-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Open Llama instruction model for multilingual chat, reasoning, and coding |
| GPT OSS 120Bopenai/gpt-oss-120b | Context window: 131,072Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.08 | Knowledge cutoff: 2024-06Released, Last updated: 2025-08-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Open GPT reasoning model for self-hosted agents and controllable deployments [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT OSS 20Bopenai/gpt-oss-20b | Context window: 131,072Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.30Cache read: 💵 $0.04 | Knowledge cutoff: 2024-06Released, Last updated: 2025-08-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Open-weight GPT model for self-hosted reasoning and instruction-following workloads [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Safety GPT OSS 20Bopenai/gpt-oss-safeguard-20b | Context window: 131,072Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.30Cache read: 💵 $0.04 | Released, Last updated: 2025-10-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Safety model for policy screening, moderation, and risk-aware routing workflows [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Llama 3.1 8Bllama-3.1-8b-instant | Context window, Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.08 | Knowledge cutoff: 2023-12Released, Last updated: 2024-07-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Compact Llama instruction model for fast chat and local deployment |
| Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m | Context window, Output limit: 512 | Input modalities, Output modalities: text | Input, Output: 💵 $0.04 | Released, Last updated: 2025-04-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Safety model for policy screening, moderation, and risk-aware routing workflows |
| Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m | Context window, Output limit: 512 | Input modalities, Output modalities: text | Input, Output: 💵 $0.03 | Released, Last updated: 2025-04-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Safety model for policy screening, moderation, and risk-aware routing workflows |
| ALLaM-2-7ballam-2-7b | Context window, Output limit: 4,096 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2025-01-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ ALLaM-2-7b instruction tuned model by SDAIA |
| Whisperwhisper-large-v3 | Context window, Output limit: 448 | Input modalities: audioOutput modalities: text | Released, Last updated: 2023-11-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Speech transcription model for accurate audio-to-text and captioning workflows | |
| Whisper Large V3 Turbowhisper-large-v3-turbo | Context window, Output limit: 448 | Input modalities: audioOutput modalities: text | Released, Last updated: 2024-10-01Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Speech transcription model for accurate audio-to-text and captioning workflows |
OpenAI 50
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| o1-proo1-pro | Context window: 200,000Output limit: 100,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $150.00Output: 💵 $600.00 | Knowledge cutoff: 2023-09Released, Last updated: 2025-03-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ O-series reasoning model for hard analysis, math, coding, and planning [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT-5.4 Progpt-5.4-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $30.00Output: 💵 $180.00 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ More exact GPT-5.4 tier for demanding professional reasoning and agent tasks [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| GPT-5.5 Progpt-5.5-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $30.00Output: 💵 $180.00 | Knowledge cutoff: 2025-12-01Released, Last updated: 2026-04-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| GPT-5.2 Progpt-5.2-pro | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $21.00Output: 💵 $168.00 | Knowledge cutoff: 2025-08-31Released, Last updated: 2025-12-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| GPT-5 Progpt-5-pro | Context window: 400,000Output limit: 272,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $15.00Output: 💵 $120.00 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-10-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning [{"type": "effort", "values": ["high"]}] |
| o3-proo3-pro | Context window: 200,000Output limit: 100,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $20.00Output: 💵 $80.00 | Knowledge cutoff: 2024-05Released, Last updated: 2025-06-10Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ High-effort o3 tier for difficult technical reasoning and careful answers [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT-4gpt-4 | Context window, Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $30.00Output: 💵 $60.00 | Knowledge cutoff: 2023-11Released: 2023-11-06Last updated: 2024-04-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT model for general reasoning, writing, coding, and tool-assisted tasks |
| Daybreak Redgpt-daybreak-red-latest | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $12.50Output: 💵 $75.00Cache read: 💵 $1.25Cache write: 💵 $15.62 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Alias for advanced cybersecurity models for authorized vulnerability research and security testing [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| o1o1 | Context window: 200,000Output limit: 100,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $15.00Output: 💵 $60.00Cache read: 💵 $7.50 | Knowledge cutoff: 2023-09Released, Last updated: 2024-12-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ O-series reasoning model for hard analysis, math, coding, and planning [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT-6 Astragpt-6-astra | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Knowledge cutoff: 2026-04-30Released, Last updated: 2026-09-04Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| GPT-4 Turbogpt-4-turbo | Context window: 128,000Output limit: 4,096 | Input modalities: text, imageOutput modalities: text | Input: 💵 $10.00Output: 💵 $30.00 | Knowledge cutoff: 2023-12Released: 2023-11-06Last updated: 2024-04-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Compact GPT model for low-latency assistance and high-volume workloads |
| GPT-5.5gpt-5.5 | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $5.00Output: 💵 $30.00Cache read: 💵 $0.50 | Knowledge cutoff: 2025-12-01Released, Last updated: 2026-04-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Default frontier GPT for coding, computer use, research, and knowledge work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-Realtime-2.1gpt-realtime-2.1 | Context window: 128,000Output limit: 32,000 | Input modalities: text, audio, imageOutput modalities: text, audio | Input: 💵 $4.00Output: 💵 $24.00Cache read: 💵 $0.40 | Knowledge cutoff: 2024-09-30Released, Last updated: 2026-07-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| GPT-5.6gpt-5.6 | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.40Cache write: 💵 $5.00 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-5.6 Solgpt-5.6-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.40Cache write: 💵 $5.00 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Daybreak Bluegpt-daybreak-blue-latest | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.40Cache write: 💵 $5.00 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Alias for flagship general-purpose models with safeguards for defensive cybersecurity work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-5.4gpt-5.4 | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.50Output: 💵 $15.00Cache read: 💵 $0.25 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Agent-ready GPT for coding and computer-use workflows at a lower cost [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-5.2gpt-5.2 | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2025-12-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Reliable GPT generation for broad coding, writing, and tool-assisted product work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-5.3 Codexgpt-5.3-codex | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-02-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Coding-optimized GPT model for repository edits, reviews, and agentic software work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-5.3 Codex Sparkgpt-5.3-codex-spark | Context window: 128,000Output limit: 32,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-02-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Coding-optimized GPT model for repository edits, reviews, and agentic software work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
GPT-4o
| Context window: 128,000Output limit:
| Input modalities:
| Input:
| Knowledge cutoff: 2023-09Released:
| 💬🖼️🔧🧠📋🔊📎🌡️ Omni-era GPT for multimodal chat, practical coding, and general assistants |
| GPT-5.6 Terragpt-5.6-terra | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Balanced GPT-5.6 model for capable, cost-efficient everyday work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-6 Solgpt-6-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-04-20Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ OpenAI model for complex coding and agentic workflows [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-6.1 Solgpt-6.1-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-04-30Released, Last updated: 2026-09-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Near-Astra performance for complex coding, computer use, and professional work at a lower cost. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| GPT-5gpt-5 | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| GPT-5.1gpt-5.1 | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-11-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sharper GPT-5 generation for coding, product work, and tool-assisted tasks [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| GPT-4.1gpt-4.1 | Context window: 1,047,576Output limit: 32,768 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $8.00Cache read: 💵 $0.50 | Knowledge cutoff: 2024-04Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Long-lived GPT workhorse for coding, instruction following, and production apps |
| o3o3 | Context window: 200,000Output limit: 100,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $8.00Cache read: 💵 $0.50 | Knowledge cutoff: 2024-05Released, Last updated: 2025-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Deliberate o-series reasoner for hard math, coding, and multi-step analysis [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT-6.1 Terragpt-6.1-terra | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | Knowledge cutoff: 2026-06-01Released, Last updated: 2026-10-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| o3-minio3-mini | Context window: 200,000Output limit: 100,000 | Input modalities, Output modalities: text | Input: 💵 $1.10Output: 💵 $4.40Cache read: 💵 $0.55 | Knowledge cutoff: 2024-05Released: 2024-12-20Last updated: 2025-01-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Smaller o-series reasoner for economical coding, math, and planning tasks [{"type": "effort", "values": ["low", "medium", "high"]}] |
| o4-minio4-mini | Context window: 200,000Output limit: 100,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.10Output: 💵 $4.40Cache read: 💵 $0.28 | Knowledge cutoff: 2024-05Released, Last updated: 2025-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast o-series model for compact reasoning, coding, and tool use [{"type": "effort", "values": ["low", "medium", "high"]}] |
| GPT-5.4 minigpt-5.4-mini | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.75Output: 💵 $4.50Cache read: 💵 $0.08 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Strong small GPT for coding subagents, quick tool use, and high-volume work [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-5 Minigpt-5-mini | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.25Output: 💵 $2.00Cache read: 💵 $0.02 | Knowledge cutoff: 2024-05-30Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Small GPT-5 for responsive agents, coding help, and everyday automation [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| GPT-3.5-turbogpt-3.5-turbo | Context window: 16,385Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $0.50Output: 💵 $1.50Cache read: 💵 $0.00 | Knowledge cutoff: 2021-09-01Released: 2023-03-01Last updated: 2023-11-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Compact GPT model for low-latency assistance and high-volume workloads |
| GPT-4.1 minigpt-4.1-mini | Context window: 1,047,576Output limit: 32,768 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $0.40Output: 💵 $1.60Cache read: 💵 $0.10 | Knowledge cutoff: 2024-04Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Affordable GPT-4.1 lane for fast coding help and structured extraction |
| GPT-5.4 nanogpt-5.4-nano | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.25Cache read: 💵 $0.02 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| GPT-5.6 Lunagpt-5.6-luna | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.20Cache read: 💵 $0.02Cache write: 💵 $0.25 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Cost-efficient GPT-5.6 model for fast, high-volume workloads [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-4o minigpt-4o-mini | Context window: 128,000Output limit: 16,384 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.08 | Knowledge cutoff: 2023-09Released, Last updated: 2024-07-18Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Small omni GPT for cheap multimodal assistance and production-scale traffic |
| GPT-6 Lunagpt-6-luna | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Knowledge cutoff: 2026-05-18Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ OpenAI's most efficient model for focused, high-volume tasks [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| GPT-4.1 nanogpt-4.1-nano | Context window: 1,047,576Output limit: 32,768 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.40Cache read: 💵 $0.02 | Knowledge cutoff: 2024-04Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Tiny GPT-4.1 option for classification, routing, and very high-volume tasks |
| GPT-5 Nanogpt-5-nano | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.40Cache read: 💵 $0.00 | Knowledge cutoff: 2024-05-30Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| text-embedding-3-largetext-embedding-3-large | Context window: 8,191Output limit: 3,072 | Input modalities, Output modalities: text | Input: 💵 $0.13Output: 💵 $0.00 | Knowledge cutoff: 2024-01Released, Last updated: 2024-01-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Embedding model for semantic search, retrieval, clustering, and ranking pipelines |
| text-embedding-ada-002text-embedding-ada-002 | Context window: 8,192Output limit: 1,536 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.00 | Knowledge cutoff: 2022-12Released, Last updated: 2022-12-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Embedding model for semantic search, retrieval, clustering, and ranking pipelines |
| text-embedding-3-smalltext-embedding-3-small | Context window: 8,191Output limit: 1,536 | Input modalities, Output modalities: text | Input: 💵 $0.02Output: 💵 $0.00 | Knowledge cutoff: 2024-01Released, Last updated: 2024-01-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Embedding model for semantic search, retrieval, clustering, and ranking pipelines |
| chatgpt-image-latestchatgpt-image-latest | Output limit: 0 | Input modalities, Output modalities: text, image | Released, Last updated: 2025-12-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Image model for prompt-driven generation, editing, and visual design workflows | |
| gpt-image-1-minigpt-image-1-mini | Output limit: 0 | Input modalities, Output modalities: text, image | Released, Last updated: 2025-09-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Image model for prompt-driven generation, editing, and visual design workflows | |
| gpt-image-1.5gpt-image-1.5 | Output limit: 0 | Input modalities, Output modalities: text, image | Released, Last updated: 2025-11-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Image model for prompt-driven generation, editing, and visual design workflows |
OpenRouter 451
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| aion-labs | |||||
| AionLabs: Aion-3.0aion-labs/aion-3.0 | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $3.00Output: 💵 $6.00Cache read: 💵 $0.75 | Released, Last updated: 2026-05-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute... |
| AionLabs: Aion 3.5aion-labs/aion-3.5 | Context window: 262,144Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $3.00Output: 💵 $6.00Cache read: 💵 $0.75 | Released, Last updated: 2026-09-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each... [{"type": "effort", "values": ["low", "high", "max"]}] |
| AionLabs: Aion-2.0aion-labs/aion-2.0 | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.80Output: 💵 $1.60Cache read: 💵 $0.20 | Released, Last updated: 2025-12-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging.... |
| AionLabs: Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b | Context window: 32,768Output limit: 29,491 | Input modalities, Output modalities: text | Input: 💵 $0.80Output: 💵 $1.60 | Knowledge cutoff: 2023-12-31Released, Last updated: 2025-02-04Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model... |
| AionLabs: Aion-3.0-Miniaion-labs/aion-3.0-mini | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.70Output: 💵 $1.40Cache read: 💵 $0.18 | Released, Last updated: 2026-05-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each... |
| AionLabs: Aion 3.5 Miniaion-labs/aion-3.5-mini | Context window: 262,144Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.70Output: 💵 $1.40Cache read: 💵 $0.18 | Released, Last updated: 2026-09-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses... [{"type": "effort", "values": ["low", "high", "max"]}] |
| amazon | |||||
| Amazon: Nova Premier 1.0amazon/nova-premier-v1 | Context window: 1,000,000Output limit: 32,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.62 | Knowledge cutoff: 2024-10Released, Last updated: 2025-04-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models. |
| Amazon: Nova Pro 1.0amazon/nova-pro-v1 | Context window: 300,000Output limit: 5,120 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.80Output: 💵 $3.20 | Knowledge cutoff: 2024-10-31Released, Last updated: 2024-12-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December... |
| Amazon: Nova 2 Liteamazon/nova-2-lite-v1 | Context window: 1,000,000Output limit: 65,535 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $0.30Output: 💵 $2.50 | Knowledge cutoff: 2025-10Released, Last updated: 2025-12-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing... [{"type": "toggle"}] |
| Amazon: Nova Lite 1.0amazon/nova-lite-v1 | Context window: 300,000Output limit: 5,120 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.06Output: 💵 $0.24 | Knowledge cutoff: 2024-10-31Released, Last updated: 2024-12-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite... |
| Amazon: Nova Micro 1.0amazon/nova-micro-v1 | Context window: 128,000Output limit: 5,120 | Input modalities, Output modalities: text | Input: 💵 $0.04Output: 💵 $0.14 | Knowledge cutoff: 2024-10-31Released, Last updated: 2024-12-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length... |
| anthracite-org | |||||
| Magnum v4 72Banthracite-org/magnum-v4-72b | Context window: 32,768Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $2.50Output: 💵 $5.00 | Knowledge cutoff: 2024-06-30Released, Last updated: 2024-10-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of Qwen2.5 72B. |
| anthropic | |||||
| Anthropic: Claude Opus 4.1anthropic/claude-opus-4.1 | Context window: 200,000Output limit: 32,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $15.00Output: 💵 $75.00Cache read: 💵 $1.50Cache write: 💵 $18.75 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-08-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains... [{"type": "toggle"}] |
| Anthropic: Claude Fable 5anthropic/claude-fable-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Knowledge cutoff: 2026-01-31Released, Last updated: 2026-06-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $0.25Cache write: 💵 $12.50 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Opus 4.1 (batch)anthropic/claude-opus-4.1:batch | Context window: 200,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $7.50Output: 💵 $37.50Cache read: 💵 $0.75Cache write: 💵 $9.38 | Knowledge cutoff: 2025-01-31 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains... |
| Anthropic: Claude Fable 5.1 (batch)anthropic/claude-fable-5.1:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.12Cache write: 💵 $6.25 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... | |
| Anthropic: Claude Fable 5 (batch)anthropic/claude-fable-5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and... | |
| Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5 | Context window: 200,000Output limit: 64,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2025-05Released, Last updated: 2025-11-24Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and... [{"type": "toggle"}] |
| Anthropic: Claude Opus 4.6anthropic/claude-opus-4.6 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2025-05-31Released: 2026-02-05Last updated: 2026-03-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective... [{"type": "effort", "values": ["none", "low", "medium", "high", "max"]}, {"type": "budget_tokens"}] |
| Anthropic: Claude Opus 4.7anthropic/claude-opus-4.7 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-01-31Released, Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-01Released, Last updated: 2026-05-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Opus 5anthropic/claude-opus-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | Knowledge cutoff: 2026-05Released, Last updated: 2026-07-24Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Opus 5.5anthropic/claude-opus-5.5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.20Cache write: 💵 $5.00 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Context window: 1,000,000Output limit: 64,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00Cache read: 💵 $0.30Cache write: 💵 $3.75 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-09-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with... [{"type": "toggle"}] |
| Anthropic: Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00Cache read: 💵 $0.30Cache write: 💵 $3.75 | Knowledge cutoff: 2025-08-31Released: 2026-02-17Last updated: 2026-03-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with... [{"type": "effort", "values": ["none", "low", "medium", "high", "max"]}] |
| Anthropic: Claude Opus 4.5 (batch)anthropic/claude-opus-4.5:batch | Context window: 200,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.25Cache write: 💵 $3.12 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and... | |
| Anthropic: Claude Opus 4.6 (batch)anthropic/claude-opus-4.6:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.25Cache write: 💵 $3.12 | 💬🖼️🔧🧠📋🔊📎🌡️ Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective... | |
| Anthropic: Claude Opus 4.7 (batch)anthropic/claude-opus-4.7:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.25Cache write: 💵 $3.12 | 💬🖼️🔧🧠📋🔊📎🌡️ Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on... | |
| Anthropic: Claude Opus 4.8 (batch)anthropic/claude-opus-4.8:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.25Cache write: 💵 $3.12 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token... | |
| Anthropic: Claude Opus 5 (batch)anthropic/claude-opus-5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.50Output: 💵 $12.50Cache read: 💵 $0.25Cache write: 💵 $3.12 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... | |
| Anthropic: Claude Opus 5.5 (batch)anthropic/claude-opus-5.5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code... | |
| Anthropic: Claude Sonnet 5anthropic/claude-sonnet-5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-01-31Released, Last updated: 2026-06-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-06Released, Last updated: 2026-09-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Sonnet 4.5 (batch)anthropic/claude-sonnet-4.5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.50Output: 💵 $7.50Cache read: 💵 $0.15Cache write: 💵 $1.88 | Knowledge cutoff: 2025-01-31 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with... |
| Anthropic: Claude Sonnet 4.6 (batch)anthropic/claude-sonnet-4.6:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.50Output: 💵 $7.50Cache read: 💵 $0.15Cache write: 💵 $1.88 | 💬🖼️🔧🧠📋🔊📎🌡️ Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with... | |
| Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5 | Context window: 200,000Output limit: 64,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.10Cache write: 💵 $1.25 | Knowledge cutoff: 2025-02-28Released, Last updated: 2025-10-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... [{"type": "toggle"}] |
| Anthropic: Claude Sonnet 5.5 (batch)anthropic/claude-sonnet-5.5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing... | |
| Anthropic: Claude Sonnet 5 (batch)anthropic/claude-sonnet-5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.10Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,... | |
| Anthropic: Claude Haiku 4.5 (batch)anthropic/claude-haiku-4.5:batch | Context window: 200,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.50Output: 💵 $2.50Cache read: 💵 $0.05Cache write: 💵 $0.62 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... | |
| Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Knowledge cutoff: 2026-06Released, Last updated: 2026-10-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Haiku 5.5 (batch)anthropic/claude-haiku-5.5:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.25Cache read: 💵 $0.00Cache write: 💵 $0.06 | 💬🖼️🔧🧠📋🔊📎🌡️ Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and... | |
| bytedance | |||||
| ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b | Context window: 128,000Output limit: 2,048 | Input modalities: image, textOutput modalities: text | Input, Cache read: 💵 $0.10Output: 💵 $0.20 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-07-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement... |
| bytedance-seed | |||||
| ByteDance Seed: Seed-2.0-Codebytedance-seed/seed-2.0-code | Context window: 262,144Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.50Output: 💵 $3.00 | Released, Last updated: 2026-02-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| ByteDance Seed: Seed 2.1 Turbobytedance-seed/seed-2-1-turbo | Context window: 262,144Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.50Output: 💵 $2.50 | Released, Last updated: 2026-06-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and... [{"type": "toggle"}] |
| ByteDance Seed: Seed 1.6bytedance-seed/seed-1.6 | Context window: 262,144Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $0.25Output: 💵 $2.00 | Released, Last updated: 2025-10-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window. [{"type": "toggle"}] |
| ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-lite | Context window: 262,144Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.25Output: 💵 $2.00 | Released, Last updated: 2026-02-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini | Context window: 262,144Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.40 | Released, Last updated: 2026-02-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash | Context window: 262,144Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.30 | Released, Last updated: 2025-08-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of... [{"type": "toggle"}] |
| cognitivecomputations | |||||
| Venice: Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-edition | Context window: 128,000Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $0.20Output: 💵 $0.90 | Knowledge cutoff: 2024-04-30Released, Last updated: 2025-07-09Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving... |
| cohere | |||||
| Cohere: Command Acohere/command-a | Context window: 256,000Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $2.50Output: 💵 $10.00 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-03-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary... |
| Cohere: Command R+ (08-2024)cohere/command-r-plus-08-2024 | Context window: 128,000Output limit: 4,000 | Input modalities, Output modalities: text | Input: 💵 $2.50Output: 💵 $10.00 | Knowledge cutoff: 2024-03-31Released, Last updated: 2024-08-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint... |
| Cohere: Command A+cohere/command-a-plus | Context window: 192,000Output limit: 64,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.30Output: 💵 $1.50Cache read: 💵 $0.15 | Knowledge cutoff: 2025-04-01Released: 2026-05-20Last updated: 2026-06-09Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured... [{"type": "toggle"}] |
| Cohere: Command R (08-2024)cohere/command-r-08-2024 | Context window: 128,000Output limit: 4,000 | Input modalities, Output modalities: text | Input: 💵 $0.15Output: 💵 $0.60 | Knowledge cutoff: 2024-03-31Released, Last updated: 2024-08-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and... |
| Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024 | Context window: 128,000Output limit: 4,000 | Input modalities, Output modalities: text | Input: 💵 $0.04Output: 💵 $0.15 | Knowledge cutoff: 2024-08-31Released, Last updated: 2024-12-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning... |
| Cohere: North Mini Code (free)cohere/north-mini-code:free | Context window: 256,000Output limit: 64,000 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Knowledge cutoff: 2025-09-23Released, Last updated: 2026-06-09Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized... [{"type": "toggle"}] |
| deepseek | |||||
| DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | Context window: 1,048,576Output limit: 393,216 | Input modalities, Output modalities: text | Input: 💵 $1.60Output: 💵 $3.20Cache read: 💵 $0.14 | Knowledge cutoff: 2025-05Released, Last updated: 2026-04-24Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,... [{"type": "effort", "values": ["none", "high", "xhigh"]}] |
| DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $4.00Cache read: 💵 $0.11 | Released: 2026-08-13Last updated: 2026-08-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: R1 0528deepseek/deepseek-r1-0528 | Context window: 163,840Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.50Output: 💵 $2.15Cache read: 💵 $0.35 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-05-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active... |
| DeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | Context window: 163,840Output limit: 115,200 | Input modalities, Output modalities: text | Input: 💵 $0.29Output: 💵 $1.14Cache read: 💵 $0.11 | Knowledge cutoff: 2024-07-31Released, Last updated: 2025-03-24Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well... |
| DeepSeek: DeepSeek V3deepseek/deepseek-chat | Context window: 163,840Output limit: 16,000 | Input modalities, Output modalities: text | Input: 💵 $0.26Output: 💵 $1.03 | Knowledge cutoff: 2024-07-31Released: 2025-12-01Last updated: 2026-02-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations... |
| DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | Context window: 163,840Output limit: 147,456 | Input modalities, Output modalities: text | Input: 💵 $0.27Output: 💵 $1.00 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-09-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's... [{"type": "toggle"}] |
| DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1 | Context window: 163,840Output limit: 147,456 | Input modalities, Output modalities: text | Input: 💵 $0.25Output: 💵 $0.95Cache read: 💵 $0.13 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-08-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context... [{"type": "toggle"}] |
| DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp | Context window: 1,048,576Output limit: 262,144 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.22Output: 💵 $0.65Cache read: 💵 $0.01 | Released: 2026-08-21Last updated: 2026-09-01Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017 | Context window: 1,048,576Output limit: 393,216 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.003 | Knowledge cutoff: 2025-05Released, Last updated: 2026-10-17Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | Context window: 163,840Output limit: 147,456 | Input modalities, Output modalities: text | Input: 💵 $0.27Output: 💵 $0.41 | Knowledge cutoff: 2025-07-31Released, Last updated: 2025-09-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... [{"type": "toggle"}] |
| DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2 | Context window: 163,840Output limit: 147,456 | Input modalities, Output modalities: text | Input: 💵 $0.26Output: 💵 $0.38Cache read: 💵 $0.13 | Knowledge cutoff: 2024-07Released, Last updated: 2025-12-01Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... [{"type": "toggle"}] |
| DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.04Output: 💵 $0.50Cache read: 💵 $0.01 | Knowledge cutoff: 2025-05Released, Last updated: 2026-09-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $0.24Cache read: 💵 $0.02 | Knowledge cutoff: 2025-05Released, Last updated: 2026-07-31Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | Context window: 1,048,576Output limit: 943,717 | Input modalities, Output modalities: text | Input: 💵 $0.09Output: 💵 $0.18Cache read: 💵 $0.02 | Knowledge cutoff: 2025-05Released, Last updated: 2026-04-24Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and... [{"type": "effort", "values": ["none", "high", "xhigh"]}] |
| DeepSeek: DeepSeek V4.1 Flash (batch)deepseek/deepseek-v4.1-flash:batch | Context window: 1,048,576 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.15Cache read: 💵 $0.004 | 💬🖼️🔧🧠📋🔊📎🌡️ DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on... | |
| dots-studio | |||||
| Dots Studio: Dots3-Note Preview (free)dots-studio/dots-3-note-preview:free | Context window: 512,000Output limit: 460,800 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-08-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is... [{"type": "toggle"}] |
| elorian | |||||
| Elorian: Glimpseelorian/glimpse | Context window: 262,144Output limit: 256,000 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.60Output: 💵 $3.00Cache read: 💵 $0.06 | Released, Last updated: 2026-10-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than... [{"type": "toggle"}] |
| fireworks | |||||
| Fireworks: Ember-1fireworks/ember-1 | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, imageOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00Cache read: 💵 $0.30 | Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| Google: Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: image, text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01Released, Last updated: 2026-05-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and... |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google/gemini-3-pro-image-preview | Context window: 65,536Output limit: 32,768 | Input modalities, Output modalities: image, text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01Released, Last updated: 2025-11-20Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and... |
| Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01Released, Last updated: 2026-02-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, audio, image, video, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01Released, Last updated: 2026-02-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini 4 Argongoogle/gemini-4-argon | Context window: 1,048,576Output limit: 943,718 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $0.19 | Knowledge cutoff: 2026-03Released, Last updated: 2026-10-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini 2.5 Progoogle/gemini-2.5-pro | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, file, audio, videoOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-06-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy... [{"type": "budget_tokens", "min": 128, "max": 32768}] |
| Google: Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: file, image, text, audioOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12Cache write: 💵 $0.38 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-06-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy... [{"type": "budget_tokens", "min": 128, "max": 32768}] |
| Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $1.50Output: 💵 $9.00Cache read: 💵 $0.15Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01-01Released, Last updated: 2026-05-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution... [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| Google: Nano Banana 2.1google/gemini-nano-banana-2.1 | Context window: 65,536Output limit: 58,982 | Input modalities, Output modalities: image, text | Input: 💵 $1.50Output: 💵 $7.50 | Released, Last updated: 2026-10-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,... [{"type": "effort", "values": ["none", "minimal", "high"]}] |
| Google: Gemini 3.1 Pro Preview (batch)google/gemini-3.1-pro-preview:batch | Context window: 1,048,576 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input: 💵 $1.00Output: 💵 $6.00 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation... | |
| Google: Gemini 4 Argon (batch)google/gemini-4-argon:batch | Context window: 1,048,576 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $0.19 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across... | |
| Google: Gemini 3.5 Flash (batch)google/gemini-3.5-flash:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.75Output: 💵 $4.50Cache read: 💵 $0.08 | Knowledge cutoff: 2025-01-01 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution... |
| Google: Gemini 3.8 Flashgoogle/gemini-3.8-flash | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.82Output: 💵 $4.12Cache read: 💵 $0.08Cache write: 💵 $0.04 | Released, Last updated: 2026-09-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.75Output: 💵 $3.75Cache read: 💵 $0.08Cache write: 💵 $0.04 | Knowledge cutoff: 2026-03Released, Last updated: 2026-07-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.75Output: 💵 $3.75Cache read: 💵 $0.08Cache write: 💵 $0.04 | Knowledge cutoff: 2026-03Released, Last updated: 2026-08-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, file, audio, videoOutput modalities: text | Input: 💵 $0.50Output: 💵 $3.00Cache read: 💵 $0.05Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01Released, Last updated: 2025-12-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image | Context window: 131,072Output limit: 32,768 | Input modalities, Output modalities: image, text | Input: 💵 $0.50Output: 💵 $3.00 | Knowledge cutoff: 2025-01Released, Last updated: 2026-05-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced... [{"type": "effort", "values": ["none", "minimal", "high"]}] |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)google/gemini-3.1-flash-image-preview | Context window: 65,536Output limit: 58,982 | Input modalities, Output modalities: image, text | Input: 💵 $0.50Output: 💵 $3.00 | Knowledge cutoff: 2025-01Released, Last updated: 2026-02-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines... [{"type": "effort", "values": ["none", "minimal", "high"]}] |
| Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | Context window: 1,048,576Output limit: 65,535 | Input modalities: file, image, text, audio, videoOutput modalities: text | Input: 💵 $0.30Output: 💵 $2.50Cache read: 💵 $0.03Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-06-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater... [{"type": "toggle"}] |
| Google: Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-image | Context window: 32,768Output limit: 8,192 | Input modalities, Output modalities: image, text | Input: 💵 $0.30Output: 💵 $2.50Cache read: 💵 $0.03Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-08-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,... |
| Google: Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.30Output: 💵 $2.50Cache read: 💵 $0.03Cache write: 💵 $0.08 | Knowledge cutoff: 2026-03Released, Last updated: 2026-07-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows. [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| Google: Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.38Output: 💵 $1.88Cache read: 💵 $0.04Cache write: 💵 $0.04 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... | |
| Google: Gemini 3.7 Flash (batch)google/gemini-3.7-flash:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.38Output: 💵 $1.88Cache read: 💵 $0.04Cache write: 💵 $0.04 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step... | |
| Google: Gemini 3.8 Flash (batch)google/gemini-3.8-flash:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.38Output: 💵 $1.88Cache read: 💵 $0.04Cache write: 💵 $0.04 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. | |
| Google: Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batch | Context window: 1,048,576 | Input modalities: text, image, file, audio, videoOutput modalities: text | Input: 💵 $0.25Output: 💵 $1.50 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool... | |
| Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.25Output: 💵 $1.50Cache read: 💵 $0.02Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01Released, Last updated: 2026-05-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-image | Context window: 65,536Output limit: 58,982 | Input modalities, Output modalities: image, text | Input: 💵 $0.25Output: 💵 $1.50 | Knowledge cutoff: 2025-01-01Released, Last updated: 2026-06-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation... [{"type": "effort", "values": ["none", "minimal", "high"]}] |
| Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.25Output: 💵 $1.50Cache read: 💵 $0.02Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01Released, Last updated: 2026-03-03Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| Google: Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.15Output: 💵 $1.25Cache read: 💵 $0.02 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows. | |
| Google: Gemma 2 27Bgoogle/gemma-2-27b-it | Context window: 8,192Output limit: 2,048 | Input modalities, Output modalities: text | Input, Output: 💵 $0.65 | Knowledge cutoff: 2024-06-30Released, Last updated: 2024-07-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of... |
| Google: Gemini 3.1 Flash Lite (batch)google/gemini-3.1-flash-lite:batch | Context window: 1,048,576 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.12Output: 💵 $0.75Cache read: 💵 $0.01 | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic... | |
| Google: Gemma 4 31Bgoogle/gemma-4-31b-it | Context window: 262,144Output limit: 16,384 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $0.20Output: 💵 $0.40 | Knowledge cutoff: 2025-01Released, Last updated: 2026-04-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function... [{"type": "toggle"}] |
| Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | Context window: 1,048,576Output limit: 65,535 | Input modalities: text, image, file, audio, videoOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.40Cache read: 💵 $0.01Cache write: 💵 $0.08 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-06-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance... [{"type": "toggle"}] |
| Google: Gemma 3 27Bgoogle/gemma-3-27b-it | Context window: 131,072Output limit: 117,964 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.35Cache read: 💵 $0.04 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-03-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... |
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | Context window: 262,144Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.25Cache read: 💵 $0.04 | Released, Last updated: 2026-04-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at... [{"type": "toggle"}] |
| Google: Gemma 3 12Bgoogle/gemma-3-12b-it | Context window: 131,072Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.15 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-03-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... |
| Google: Gemma 3 4Bgoogle/gemma-3-4b-it | Context window: 131,072Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.10 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-03-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... |
| Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | Context window: 262,144Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-04-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at... [{"type": "toggle"}] |
| Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | Context window: 262,144Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input, Output: 💵 $0.00 | Knowledge cutoff: 2025-01Released, Last updated: 2026-04-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function... [{"type": "toggle"}] |
| Google: Lyria 3 Clip Previewgoogle/lyria-3-clip-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, imageOutput modalities: text, audio | Input, Output: 💵 $0.00 | Released, Last updated: 2026-03-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ 30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate... |
| Google: Lyria 3 Pro Previewgoogle/lyria-3-pro-preview | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, imageOutput modalities: text, audio | Input, Output: 💵 $0.00 | Released, Last updated: 2026-03-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz... |
| gryphe | |||||
| MythoMax 13Bgryphe/mythomax-l2-13b | Context window: 8,192Output limit: 3,686 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.11 | Knowledge cutoff: 2023-06-30Released, Last updated: 2023-08-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge |
| ibm-granite | |||||
| IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $0.06Output: 💵 $0.15Cache read: 💵 $0.02 | Released, Last updated: 2026-08-25Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,... [{"type": "effort", "values": ["none", "low", "high"]}] |
| inception | |||||
| Inception: Mercury 2inception/mercury-2 | Context window: 128,000Output limit: 50,000 | Input modalities, Output modalities: text | Input: 💵 $0.25Output: 💵 $0.75Cache read: 💵 $0.02 | Released, Last updated: 2026-02-24Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| Inception: Mercury 3inception/mercury-3 | Context window: 1,000,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.35Cache read: 💵 $0.01 | Released, Last updated: 2026-10-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| Inception: Mercury 2.5inception/mercury-2.5 | Context window: 260,000Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.04Output: 💵 $0.15Cache read: 💵 $0.004 | Released, Last updated: 2026-09-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| inclusionai | |||||
| inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flash | Context window: 1,000,000Output limit: 262,144 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.22Cache read: 💵 $0.02 | Released, Last updated: 2026-09-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. [{"type": "toggle"}] |
| inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | Context window: 131,072Output limit: 32,768 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.06Output: 💵 $0.18Cache read: 💵 $0.01 | Released, Last updated: 2026-09-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual... [{"type": "toggle"}] |
| inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash | Context window: 262,144Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.02Output: 💵 $0.06Cache read: 💵 $0.004 | Released, Last updated: 2026-07-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers... [{"type": "toggle"}] |
| inference-net | |||||
| Inference.net: Schematron V2 Smallinference-net/schematron-v2-small | Context window: 128,000Output limit: 4,096 | Input modalities, Output modalities: text | Input, Cache read: 💵 $0.05Output: 💵 $0.23 | Released, Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema... |
| Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbo | Context window: 128,000Output limit: 8,192 | Input modalities, Output modalities: text | Input, Cache read: 💵 $0.03Output: 💵 $0.15 | Released, Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather... |
| liquid | |||||
| LiquidAI: LFM2.5-2.6Bliquid/lfm-2.5-2.6b | Context window: 128,000Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $0.35Output: 💵 $0.50Cache read: 💵 $0.04 | Released, Last updated: 2026-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or... |
| LiquidAI: LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b | Context window: 128,000Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.70Cache read: 💵 $0.02 | Released, Last updated: 2026-10-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid... |
| LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:free | Context window: 65,536Output limit: 8,192 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or... |
| mancer | |||||
| Mancer: Weaver (alpha)mancer/weaver | Context window: 8,000Output limit: 6,000 | Input modalities, Output modalities: text | Input: 💵 $0.40Output: 💵 $0.75 | Knowledge cutoff: 2023-06-30Released, Last updated: 2023-08-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations. |
| meituan | |||||
| Meituan: LongCat 2.0meituan/longcat-2.0 | Context window: 1,048,756Output limit: 262,144 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.01 | Released, Last updated: 2026-06-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic... [{"type": "toggle"}, {"type": "budget_tokens"}] |
| meta | |||||
| Meta: Muse Wondermeta/muse-wonder | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.20 | Released, Last updated: 2026-10-12Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"]}] |
| Meta: Muse Spark 1.1meta/muse-spark-1.1 | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $4.25Cache read: 💵 $0.15 | Released: 2026-04-08Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window.... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| Meta: Muse Spark 1.2meta/muse-spark-1.2 | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $4.25Cache read: 💵 $0.15 | Released, Last updated: 2026-08-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window.... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| Meta: Muse Spark 1.3meta/muse-spark-1.3 | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $4.25Cache read: 💵 $0.15 | Released, Last updated: 2026-09-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"]}] |
| Meta: Muse Spark Openmeta/muse-spark-open | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $1.25Output: 💵 $4.25Cache read: 💵 $0.15 | Knowledge cutoff: 2026-01-04Released, Last updated: 2026-10-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b | Context window: 131,072Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.04 | Knowledge cutoff: 2026-01-04Released, Last updated: 2026-08-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.20Cache read: 💵 $0.002 | Released, Last updated: 2026-08-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, video, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.20Cache read: 💵 $0.002 | Released, Last updated: 2026-09-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"]}] |
| meta-llama | |||||
| Meta: Llama 4 Maverickmeta-llama/llama-4-maverick | Context window: 524,288Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.19Output: 💵 $0.65Cache read: 💵 $0.05 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-04-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward... |
| Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct | Context window: 131,072Output limit: 16,384 | Input modalities, Output modalities: text | Input, Output: 💵 $0.40 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-07-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong... |
| Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Context window: 131,072Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.32 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-12-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model... |
| Meta: Llama 4 Scoutmeta-llama/llama-4-scout | Context window: 1,310,720Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.30 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-04-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input... |
| Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct | Context window: 131,072Output limit: 72,000 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.34 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-09-25Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it... |
| Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12b | Context window: 163,840Output limit: 16,384 | Input modalities: image, textOutput modalities: text | Input, Output: 💵 $0.18 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-04-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM... |
| Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct | Context window: 60,000Output limit: 54,000 | Input modalities, Output modalities: text | Input: 💵 $0.03Output: 💵 $0.20 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-09-25Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate... |
| Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.08Cache read: 💵 $0.02 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-07-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to... |
| microsoft | |||||
| Microsoft: Phi 4microsoft/phi-4 | Context window: 16,384Output limit: 14,745 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.14 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-01-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion... |
| minimax | |||||
| MiniMax: MiniMax M1minimax/minimax-m1 | Context window: 1,000,000Output limit: 40,000 | Input modalities, Output modalities: text | Input: 💵 $0.55Output: 💵 $2.20 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-06-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it... [{"type": "toggle"}] |
| MiniMax: MiniMax M2-herminimax/minimax-m2-her | Context window: 65,536Output limit: 2,048 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.03 | Released, Last updated: 2026-01-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message... |
| MiniMax: MiniMax M2.1minimax/minimax-m2.1 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.03 | Released, Last updated: 2025-12-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world... |
| MiniMax: MiniMax M2.7minimax/minimax-m2.7 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.06 | Released, Last updated: 2026-03-18Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent... |
| MiniMax: MiniMax M3minimax/minimax-m3 | Context window: 1,048,576Output limit: 512,000 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.30Output: 💵 $1.20Cache read: 💵 $0.06 | Released, Last updated: 2026-06-01Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,... [{"type": "toggle"}] |
| MiniMax: MiniMax-01minimax/minimax-01 | Context window: 1,000,192Output limit: 40,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.10 | Knowledge cutoff: 2024-03-31Released, Last updated: 2025-01-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context... |
| MiniMax: MiniMax M2minimax/minimax-m2 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.26Output: 💵 $1.02 | Released, Last updated: 2025-10-27Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,... |
| MiniMax: MiniMax M2.5minimax/minimax-m2.5 | Context window: 204,800Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.27Output: 💵 $0.95Cache read: 💵 $0.03 | Released, Last updated: 2026-02-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1... |
| MiniMax: MiniMax M3.1 Flashminimax/minimax-m3.1-flash | Context window: 1,048,576Output limit: 524,288 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.30Cache read: 💵 $0.01 | Released, Last updated: 2026-10-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| mistralai | |||||
| Mistral: Mistral Medium 3.5mistralai/mistral-medium-3-5 | Context window: 262,144Output limit: 209,715 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.50Output: 💵 $7.50 | Released, Last updated: 2026-04-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... [{"type": "effort", "values": ["none", "high"]}] |
| Mistral Largemistralai/mistral-large | Context window: 128,000Output limit: 102,400 | Input modalities: text, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.20 | Knowledge cutoff: 2024-11-30Released, Last updated: 2024-02-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This is Mistral AI's flagship model, Mistral Large 2 (version |
| Mistral Large 2407mistralai/mistral-large-2407 | Context window: 131,072Output limit: 104,857 | Input modalities: text, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.20 | Knowledge cutoff: 2024-03-31Released, Last updated: 2024-07-24Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.... |
| Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Context window: 65,536Output limit: 52,428 | Input modalities: text, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.20 | Knowledge cutoff: 2024-01-31Released, Last updated: 2024-04-17Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,... |
| Mistral: Mistral Medium 3.5 (batch)mistralai/mistral-medium-3-5:batch | Context window: 262,144 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.75Output: 💵 $3.75 | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... | |
| Mistral: Mistral Large 4mistralai/mistral-large-4-0 | Context window: 1,048,576Output limit: 262,144 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.70Output: 💵 $2.10Cache read: 💵 $0.07 | Released, Last updated: 2026-10-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Mistral: Devstral 2 2512mistralai/devstral-2512 | Context window: 262,144Output limit: 209,715 | Input modalities: text, fileOutput modalities: text | Input: 💵 $0.40Output: 💵 $2.00Cache read: 💵 $0.04 | Knowledge cutoff: 2025-12Released, Last updated: 2025-12-09Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring... |
| Mistral: Mistral Medium 3mistralai/mistral-medium-3 | Context window: 131,072Output limit: 104,857 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.40Output: 💵 $2.00Cache read: 💵 $0.04 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-05-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost... |
| Mistral: Mistral Medium 3.1mistralai/mistral-medium-3.1 | Context window: 131,072Output limit: 104,857 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.40Output: 💵 $2.00Cache read: 💵 $0.04 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-08-12Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances... |
| Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 | Context window: 262,144Output limit: 209,715 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.50Output: 💵 $1.50Cache read: 💵 $0.05 | Knowledge cutoff: 2024-11Released, Last updated: 2025-12-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license. |
| Mistral: Codestral 2508mistralai/codestral-2508 | Context window: 256,000Output limit: 204,800 | Input modalities: text, fileOutput modalities: text | Input: 💵 $0.30Output: 💵 $0.90Cache read: 💵 $0.03 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-07-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. |
| Mistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct | Context window: 128,000Output limit: 102,400 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.35Output: 💵 $0.56 | Knowledge cutoff: 2023-10-31Released, Last updated: 2025-03-17Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and... |
| Mistral: Sabamistralai/mistral-saba | Context window: 32,768Output limit: 26,214 | Input modalities: text, fileOutput modalities: text | Input: 💵 $0.20Output: 💵 $0.60Cache read: 💵 $0.02 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-02-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional... |
| Mistral: Mistral Small 4mistralai/mistral-small-2603 | Context window: 262,144Output limit: 209,715 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.02 | Knowledge cutoff: 2025-06Released, Last updated: 2026-03-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from... [{"type": "effort", "values": ["none", "high"]}] |
| Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 | Context window: 262,144Output limit: 209,715 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.20Cache read: 💵 $0.02 | Released, Last updated: 2025-12-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language... |
| Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507 | Context window: 32,768Output limit: 26,214 | Input modalities: text, audio, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.30Cache read: 💵 $0.01 | Released, Last updated: 2025-07-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio... |
| Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | Context window: 262,144Output limit: 209,715 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.15Cache read: 💵 $0.02 | Released, Last updated: 2025-12-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities. |
| Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct | Context window: 256,000Output limit: 16,384 | Input modalities: image, textOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.20 | Knowledge cutoff: 2023-10-31Released, Last updated: 2025-06-20Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on... |
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | Context window: 131,072Output limit: 104,857 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.10Cache read: 💵 $0.01 | Released, Last updated: 2025-12-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. |
| Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | Context window: 32,768Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.08 | Knowledge cutoff: 2023-10-31Released, Last updated: 2025-01-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed... |
| Mistral: Mistral Nemomistralai/mistral-nemo | Context window: 131,072Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.03Output: 💵 $0.03 | Knowledge cutoff: 2024-04-30Released, Last updated: 2024-07-18Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,... |
| moondream | |||||
| Moondream: Moondream 3 Previewmoondream/moondream3-preview | Context window: 32,000Output limit: 4,096 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.30Output: 💵 $2.50 | Released, Last updated: 2026-10-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with... [{"type": "toggle"}] |
| Moondream: Moondream 3.1moondream/moondream3.1-9b-a2b | Context window: 32,000Output limit: 4,096 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.30Output: 💵 $2.50 | Released, Last updated: 2026-10-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and... [{"type": "toggle"}] |
| moonshotai | |||||
| MoonshotAI: Kimi K3moonshotai/kimi-k3 | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.19Output: 💵 $15.00Cache read: 💵 $0.18 | Released, Last updated: 2026-07-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batch | Context window: 1,048,576 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $2.28Output: 💵 $11.40Cache read: 💵 $0.23 | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at... | |
| MoonshotAI: Kimi K3.1 Promoonshotai/kimi-k3.1-pro | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20 | Released, Last updated: 2026-10-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D... [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.60Output: 💵 $3.50Cache read: 💵 $0.15 | Knowledge cutoff: 2025-01Released, Last updated: 2026-06-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts... |
| MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6 | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.65Output: 💵 $3.41Cache read: 💵 $0.15 | Knowledge cutoff: 2025-01Released, Last updated: 2026-04-20Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and... [{"type": "toggle"}] |
| MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905 | Context window: 262,144Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.50 | Knowledge cutoff: 2024-12-31Released, Last updated: 2025-09-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32... |
| MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Context window: 262,144Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.50Cache read: 💵 $0.15 | Knowledge cutoff: 2024-08Released, Last updated: 2025-11-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in... |
| MoonshotAI: Kimi K2.5moonshotai/kimi-k2.5 | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.50Output: 💵 $2.50Cache read: 💵 $0.15 | Knowledge cutoff: 2025-01Released, Last updated: 2026-01-27Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed... [{"type": "toggle"}] |
| MoonshotAI: Kimi K2 0711moonshotai/kimi-k2 | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.57Output: 💵 $2.30 | Knowledge cutoff: 2024-12-31Released, Last updated: 2025-07-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for... |
| morph | |||||
| Morph: Morph V3 Largemorph/morph-v3-large | Context window: 262,144Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.90Output: 💵 $1.90 | Released, Last updated: 2025-07-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} |
| Morph: Morph V3 Fastmorph/morph-v3-fast | Context window: 262,144Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.80Output: 💵 $1.20 | Released, Last updated: 2025-07-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} |
| nex-agi | |||||
| Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-pro | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.25Cache read: 💵 $0.02 | Released, Last updated: 2026-09-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file... [{"type": "effort", "values": ["none", "medium", "high"]}] |
| Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-mini | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.02Output: 💵 $0.10Cache read: 💵 $0.003 | Released, Last updated: 2026-09-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file... [{"type": "effort", "values": ["none", "medium", "high"]}] |
| nousresearch | |||||
| Nous: Hermes 4 405Bnousresearch/hermes-4-405b | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $1.00Output: 💵 $3.00Cache read: 💵 $0.20 | Knowledge cutoff: 2024-08-31Released, Last updated: 2025-08-26Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with... [{"type": "toggle"}] |
| nvidia | |||||
| NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | Context window: 262,144Output limit: 182,520 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.40Cache read: 💵 $0.12 | Knowledge cutoff: 2025-09Released, Last updated: 2026-06-04Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... [{"type": "effort", "values": ["none", "medium", "high"]}, {"type": "budget_tokens"}] |
| NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | Context window: 1,048,576Output limit: 262,144 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $2.40Cache read: 💵 $0.15 | Knowledge cutoff: 2025-06Released, Last updated: 2026-03-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer... [{"type": "effort", "values": ["none", "low", "medium"]}, {"type": "budget_tokens"}] |
| NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | Context window: 1,048,576Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.50Cache read: 💵 $0.02 | Released, Last updated: 2026-10-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety | Context window: 131,072Output limit: 117,964 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.20 | Released, Last updated: 2026-06-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.06Output: 💵 $0.24Cache read: 💵 $0.01 | Knowledge cutoff: 2025-06-25Released, Last updated: 2025-12-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.20Cache read: 💵 $0.04 | Knowledge cutoff: 2025-09Released, Last updated: 2026-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Context window: 256,000Output limit: 65,536 | Input modalities: text, audio, image, videoOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-04-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and... [{"type": "toggle"}, {"type": "budget_tokens"}] |
| NVIDIA: Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:free | Context window: 1,000,000Output limit: 65,536 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Knowledge cutoff: 2025-09Released, Last updated: 2026-06-04Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... [{"type": "effort", "values": ["none", "medium", "high"]}, {"type": "budget_tokens"}] |
| NVIDIA: Nemotron 3.5 Content Safety (free)nvidia/nemotron-3.5-content-safety:free | Context window: 128,000Output limit: 8,192 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-06-02Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:free | Context window: 1,000,000Output limit: 65,536 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Knowledge cutoff: 2025-09Released, Last updated: 2026-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that... [{"type": "toggle"}] |
| NVIDIA: Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:free | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-10-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... [{"type": "toggle"}] |
| NVIDIA: Switchyardnvidia/switchyard | Context window: 1,000,000 | Input modalities, Output modalities: text | Input, Output: 💵 -$1,000,000.00 | 💬🖼️🔧🧠📋🔊📎🌡️ Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most... | |
| openai | |||||
| OpenAI: GPT-5.4 Proopenai/gpt-5.4-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $30.00Output: 💵 $180.00 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K... [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.5 Proopenai/gpt-5.5-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $30.00Output: 💵 $180.00 | Knowledge cutoff: 2025-12-01Released, Last updated: 2026-04-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for... [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.2 Proopenai/gpt-5.2-pro | Context window: 400,000Output limit: 128,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $21.00Output: 💵 $168.00 | Knowledge cutoff: 2025-08-31Released, Last updated: 2025-12-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,... [{"type": "effort", "values": ["medium", "high", "xhigh"]}] |
| OpenAI: GPT-5 Proopenai/gpt-5-pro | Context window: 400,000Output limit: 128,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $15.00Output: 💵 $120.00 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-10-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and... [{"type": "effort", "values": ["high"]}] |
| OpenAI: GPT-5.4 Pro (batch)openai/gpt-5.4-pro:batch | Context window: 1,050,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $15.00Output: 💵 $90.00 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K... | |
| OpenAI: GPT-5.5 Pro (batch)openai/gpt-5.5-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $15.00Output: 💵 $90.00 | Knowledge cutoff: 2025-12-01 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for... |
| OpenAI: o3 Proopenai/o3-pro | Context window: 200,000Output limit: 100,000 | Input modalities: text, file, imageOutput modalities: text | Input: 💵 $20.00Output: 💵 $80.00 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-06-10Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently... [{"type": "toggle"}] |
| OpenAI: GPT-5.2 Pro (batch)openai/gpt-5.2-pro:batch | Context window: 400,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $10.50Output: 💵 $84.00 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,... | |
| OpenAI: GPT-4openai/gpt-4 | Context window: 8,191Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $30.00Output: 💵 $60.00 | Knowledge cutoff: 2021-09-30Released: 2023-11-06Last updated: 2024-04-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning... |
| OpenAI: GPT-5 Pro (batch)openai/gpt-5-pro:batch | Context window: 400,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $7.50Output: 💵 $60.00 | Knowledge cutoff: 2024-09-30 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and... |
| OpenAI: GPT-6 Astraopenai/gpt-6-astra | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Knowledge cutoff: 2026-04-30Released, Last updated: 2026-09-04Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6 Astra Proopenai/gpt-6-astra-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Released, Last updated: 2026-09-04Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.5openai/gpt-5.5 | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $5.00Output: 💵 $30.00Cache read: 💵 $0.50 | Knowledge cutoff: 2025-12-01Released, Last updated: 2026-04-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT Chat Latestopenai/gpt-chat-latest | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $30.00Cache read: 💵 $0.50 | Released, Last updated: 2026-05-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT Chat Latest points to OpenAI's stable API alias |
| OpenAI: GPT-6 Astra Pro (batch)openai/gpt-6-astra-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with | |
| OpenAI: GPT-6 Astra (batch)openai/gpt-6-astra:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $5.00Output: 💵 $25.00Cache read: 💵 $0.50Cache write: 💵 $6.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon... | |
| OpenAI: GPT-5.6 Solopenai/gpt-5.6-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.40Cache write: 💵 $5.00 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.40Cache write: 💵 $5.00 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.4 Image 2openai/gpt-5.4-image-2 | Context window: 272,000Output limit: 128,000 | Input modalities: image, text, fileOutput modalities: image, text | Input: 💵 $8.00Output: 💵 $15.00Cache read: 💵 $2.00 | Released, Last updated: 2026-04-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-4 Turbo (batch)openai/gpt-4-turbo:batch | Context window: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $5.00Output: 💵 $15.00 | Knowledge cutoff: 2023-12-31 | 💬🖼️🔧🧠📋🔊📎🌡️ The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023. |
| OpenAI: GPT-5 Imageopenai/gpt-5-image | Context window: 400,000Output limit: 128,000 | Input modalities: image, text, fileOutput modalities: image, text | Input, Output: 💵 $10.00Cache read: 💵 $1.25 | Knowledge cutoff: 2024-10-01Released, Last updated: 2025-10-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,... |
| OpenAI: GPT-5.4openai/gpt-5.4 | Context window: 1,050,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.50Output: 💵 $15.00Cache read: 💵 $0.25 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.5 (batch)openai/gpt-5.5:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.50Output: 💵 $15.00Cache read: 💵 $0.25 | Knowledge cutoff: 2025-12-01 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token... |
| OpenAI: GPT-5.2openai/gpt-5.2 | Context window: 400,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2025-12-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chat | Context window: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on... | |
| OpenAI: GPT-5.2-Codexopenai/gpt-5.2-codex | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2025-12-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codex | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.75Output: 💵 $14.00Cache read: 💵 $0.18 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-02-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
OpenAI: GPT-4o
| Context window: 128,000Output limit:
| Input modalities: text, image, fileOutput modalities: text | Input:
| Knowledge cutoff: 2023-10-31Released:
| 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as... |
| OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terra | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $12.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT Audioopenai/gpt-audio | Context window: 128,000Output limit: 16,384 | Input modalities, Output modalities: text, audio | Input: 💵 $2.50Output: 💵 $10.00 | Knowledge cutoff: 2023-10-01Released, Last updated: 2025-08-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced... |
| OpenAI: GPT-5.6 Sol Pro (batch)openai/gpt-5.6-sol-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with |
| OpenAI: GPT-5.6 Sol (batch)openai/gpt-5.6-sol:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks... |
| OpenAI: GPT-6 Solopenai/gpt-6-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Knowledge cutoff: 2026-04-20Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6 Sol Proopenai/gpt-6-sol-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.20Cache write: 💵 $2.50 | Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-04-30Released, Last updated: 2026-09-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Released, Last updated: 2026-09-29Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5openai/gpt-5 | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy... [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| OpenAI: GPT-5.1openai/gpt-5.1 | Context window: 400,000Output limit: 128,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-11-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| OpenAI: GPT-5.1-Codexopenai/gpt-5.1-codex | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.13 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-11-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| OpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-max | Context window: 400,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $1.25Output: 💵 $10.00Cache read: 💵 $0.12 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-11-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-4.1openai/gpt-4.1 | Context window: 1,047,576Output limit: 32,768 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $8.00Cache read: 💵 $0.50 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and... |
| OpenAI: o3openai/o3 | Context window: 200,000Output limit: 100,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $8.00Cache read: 💵 $0.50 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following.... [{"type": "toggle"}] |
| OpenAI: GPT-5.4 (batch)openai/gpt-5.4:batch | Context window: 1,050,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $7.50Cache read: 💵 $0.12 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for... | |
| OpenAI: GPT-5.2 (batch)openai/gpt-5.2:batch | Context window: 400,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.88Output: 💵 $7.00Cache read: 💵 $0.09 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly... | |
| OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k | Context window: 16,385Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $3.00Output: 💵 $4.00 | Knowledge cutoff: 2021-09-30Released, Last updated: 2023-08-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up... |
| OpenAI: GPT-5.6 Terra Pro (batch)openai/gpt-5.6-terra-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $6.00Cache read: 💵 $0.10 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with |
| OpenAI: GPT-5.6 Terra (batch)openai/gpt-5.6-terra:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $6.00Cache read: 💵 $0.10 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic... |
| OpenAI: GPT-4o (batch)openai/gpt-4o:batch | Context window: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $5.00Cache read: 💵 $0.62 | Knowledge cutoff: 2023-10-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as... |
| OpenAI: GPT-6 Sol Pro (batch)openai/gpt-6-sol-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.10Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with | |
| OpenAI: GPT-6 Sol (batch)openai/gpt-6-sol:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.10Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional... | |
| OpenAI: GPT-6.1 Sol Pro (batch)openai/gpt-6.1-sol-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with | |
| OpenAI: GPT-6.1 Sol (batch)openai/gpt-6.1-sol:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional... | |
| OpenAI: GPT-6.1 Terraopenai/gpt-6.1-terra | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | Knowledge cutoff: 2026-06-01Released, Last updated: 2026-10-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6.1 Terra Proopenai/gpt-6.1-terra-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | Released, Last updated: 2026-10-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.1 (batch)openai/gpt-5.1:batch | Context window: 400,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.62Output: 💵 $5.00Cache read: 💵 $0.06 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning... | |
| OpenAI: GPT-5 (batch)openai/gpt-5:batch | Context window: 400,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.62Output: 💵 $5.00Cache read: 💵 $0.06 | Knowledge cutoff: 2024-09-30 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy... |
| OpenAI: GPT-5.4 Miniopenai/gpt-5.4-mini | Context window: 400,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.75Output: 💵 $4.50Cache read: 💵 $0.08 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-4.1 (batch)openai/gpt-4.1:batch | Context window: 1,047,576 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $4.00Cache read: 💵 $0.25 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and... |
| OpenAI: o3 (batch)openai/o3:batch | Context window: 200,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $4.00Cache read: 💵 $0.25 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following.... |
| OpenAI: GPT-5 Image Miniopenai/gpt-5-image-mini | Context window: 400,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: image, text | Input: 💵 $2.50Output: 💵 $2.00Cache read: 💵 $0.25 | Released, Last updated: 2025-10-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text... |
| OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613 | Context window: 4,095Output limit: 3,685 | Input modalities, Output modalities: text | Input: 💵 $1.00Output: 💵 $2.00 | Knowledge cutoff: 2021-09-30Released, Last updated: 2024-01-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021. |
| OpenAI: GPT-6.1 Terra Pro (batch)openai/gpt-6.1-terra-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.50Output: 💵 $2.50Cache read: 💵 $0.02Cache write: 💵 $0.62 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with | |
| OpenAI: GPT-6.1 Terra (batch)openai/gpt-6.1-terra:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.50Output: 💵 $2.50Cache read: 💵 $0.02Cache write: 💵 $0.62 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots... | |
| OpenAI: GPT Audio Miniopenai/gpt-audio-mini | Context window: 128,000Output limit: 16,384 | Input modalities, Output modalities: text, audio | Input: 💵 $0.60Output: 💵 $2.40 | Knowledge cutoff: 2023-10-01Released, Last updated: 2025-10-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million... |
| OpenAI: o3 Mini (batch)openai/o3-mini:batch | Context window: 200,000 | Input modalities: text, fileOutput modalities: text | Input: 💵 $0.55Output: 💵 $2.20Cache read: 💵 $0.28 | Knowledge cutoff: 2023-10-31 | 💬🖼️🔧🧠📋🔊📎🌡️ OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the |
| OpenAI: o4 Mini (batch)openai/o4-mini:batch | Context window: 200,000 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.55Output: 💵 $2.20Cache read: 💵 $0.14 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning... |
| OpenAI: GPT-5.4 Mini (batch)openai/gpt-5.4-mini:batch | Context window: 400,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.38Output: 💵 $2.25Cache read: 💵 $0.04 | Knowledge cutoff: 2025-08-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,... |
| OpenAI: GPT-5 Miniopenai/gpt-5-mini | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.25Output: 💵 $2.00Cache read: 💵 $0.02 | Knowledge cutoff: 2024-05-31Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost.... [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | Context window: 400,000Output limit: 128,000 | Input modalities: image, textOutput modalities: text | Input: 💵 $0.25Output: 💵 $2.00Cache read: 💵 $0.03 | Knowledge cutoff: 2024-09-30Released, Last updated: 2025-11-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex [{"type": "effort", "values": ["low", "medium", "high"]}] |
| OpenAI: GPT-4.1 Miniopenai/gpt-4.1-mini | Context window: 1,047,576Output limit: 32,768 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.40Output: 💵 $1.60Cache read: 💵 $0.10 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard... |
| OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano | Context window: 400,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.25Cache read: 💵 $0.02 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-03-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.20Cache read: 💵 $0.02Cache write: 💵 $0.25 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.20Cache read: 💵 $0.02Cache write: 💵 $0.25 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-07-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-5 Mini (batch)openai/gpt-5-mini:batch | Context window: 400,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.12Output: 💵 $1.00Cache read: 💵 $0.01 | Knowledge cutoff: 2024-05-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost.... |
| OpenAI: GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batch | Context window: 1,047,576 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.20Output: 💵 $0.80Cache read: 💵 $0.05 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard... |
OpenAI: GPT-4o-mini
| Context window: 128,000Output limit: 16,384 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.08 | Knowledge cutoff: 2023-10-31Released: 2024-07-18Last updated: 2024-07-18Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable... |
| OpenAI: gpt-oss-120bopenai/gpt-oss-120b | Context window: 131,072Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.08 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-08-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| OpenAI: GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batch | Context window: 400,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.62Cache read: 💵 $0.01 | Knowledge cutoff: 2025-08-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency... |
| OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.60Cache read: 💵 $0.01 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with |
| OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.60Cache read: 💵 $0.01 | Knowledge cutoff: 2026-02-16 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for... |
| OpenAI: GPT-6 Lunaopenai/gpt-6-luna | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Knowledge cutoff: 2026-05-18Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic... [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-pro | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano | Context window: 1,047,576Output limit: 942,818 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.40Cache read: 💵 $0.03 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-04-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million... |
| OpenAI: GPT-5 Nanoopenai/gpt-5-nano | Context window: 400,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.40Cache read: 💵 $0.00 | Knowledge cutoff: 2024-05-31Released, Last updated: 2025-08-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger... [{"type": "effort", "values": ["minimal", "low", "medium", "high"]}] |
| OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batch | Context window: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.30Cache read: 💵 $0.04 | Knowledge cutoff: 2023-10-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable... |
| OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b | Context window: 131,072Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.30Cache read: 💵 $0.04 | Released, Last updated: 2025-10-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| OpenAI: GPT-6 Luna Pro (batch)openai/gpt-6-luna-pro:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.25Cache read: 💵 $0.00Cache write: 💵 $0.06 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with | |
| OpenAI: GPT-6 Luna (batch)openai/gpt-6-luna:batch | Context window: 1,050,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.25Cache read: 💵 $0.00Cache write: 💵 $0.06 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic... | |
| OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | Context window: 1,047,576 | Input modalities: image, text, fileOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.20Cache read: 💵 $0.01 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million... |
| OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch | Context window: 400,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.02Output: 💵 $0.20Cache read: 💵 $0.003 | Knowledge cutoff: 2024-05-31 | 💬🖼️🔧🧠📋🔊📎🌡️ GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger... |
| OpenAI: gpt-oss-120b (batch)openai/gpt-oss-120b:batch | Context window: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.03Output: 💵 $0.14 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized... |
| OpenAI: gpt-oss-20bopenai/gpt-oss-20b | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input, Cache read: 💵 $0.03Output: 💵 $0.13 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-08-05Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch | Context window: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.02Output: 💵 $0.11 | Knowledge cutoff: 2024-06-30 | 💬🖼️🔧🧠📋🔊📎🌡️ gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for... |
| openrouter | |||||
| Free Models Routeropenrouter/free | Context window: 200,000Output limit: 8,000 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-02-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that... |
| Auto Routeropenrouter/auto | Context window, Output limit: 2,000,000 | Input modalities: text, image, audio, file, videoOutput modalities: text, image | Input, Output: 💵 -$1,000,000.00 | Released, Last updated: 2023-11-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on... |
| Auto Router (Beta)openrouter/auto-beta | Context window: 2,000,000 | Input modalities: text, image, audio, file, videoOutput modalities: text, image | Input, Output: 💵 -$1,000,000.00 | 💬🖼️🔧🧠📋🔊📎🌡️ The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta... | |
| Body Builder (beta)openrouter/bodybuilder | Context window, Output limit: 128,000 | Input modalities, Output modalities: text | Input, Output: 💵 -$1,000,000.00 | Released, Last updated: 2025-12-05Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:... |
| OpenRouter: Fusionopenrouter/fusion | Context window: 1,000,000Output limit: 128,000 | Input modalities, Output modalities: text | Input, Output: 💵 -$1,000,000.00 | Released, Last updated: 2026-06-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a... |
| Pareto Code Routeropenrouter/pareto-code | Context window: 2,000,000Output limit: 200,000 | Input modalities, Output modalities: text | Input, Output: 💵 -$1,000,000.00 | Released, Last updated: 2026-04-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router plugin t… |
| particle-ai | |||||
| Particle AI: Particle-1particle-ai/particle-1 | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.50Cache read: 💵 $0.003 | Released, Last updated: 2026-10-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"]}] |
| perceptron | |||||
| Perceptron: Perceptron Mk1perceptron/perceptron-mk1 | Context window: 32,768Output limit: 8,192 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $1.50 | Released, Last updated: 2026-05-12Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding... [{"type": "toggle"}] |
| Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.5 | Context window: 36,864Output limit: 8,192 | Input modalities: text, image, video, audioOutput modalities: text | Input: 💵 $0.15Output: 💵 $1.50 | Released, Last updated: 2026-09-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high"]}] |
| perplexity | |||||
| Perplexity: Sonar Properplexity/sonar-pro | Context window: 200,000Output limit: 8,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00 | Released, Last updated: 2025-03-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibilit… |
| Perplexity: Sonar Pro Searchperplexity/sonar-pro-search | Context window: 200,000Output limit: 8,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $3.00Output: 💵 $15.00 | Released, Last updated: 2025-10-30Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based... |
| Perplexity: Sonar Deep Researchperplexity/sonar-deep-research | Context window: 128,000Output limit: 115,200 | Input modalities, Output modalities: text | Input: 💵 $2.00Output: 💵 $8.00 | Released, Last updated: 2025-03-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers... [{"type": "toggle"}] |
| Perplexity: Sonar Reasoning Properplexity/sonar-reasoning-pro | Context window: 128,000Output limit: 115,200 | Input modalities: text, imageOutput modalities: text | Input: 💵 $2.00Output: 💵 $8.00 | Released, Last updated: 2025-03-07Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for... [{"type": "toggle"}] |
| Perplexity: Sonarperplexity/sonar | Context window: 127,072Output limit: 114,364 | Input modalities: text, imageOutput modalities: text | Input, Output: 💵 $1.00 | Released, Last updated: 2025-01-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features... |
| prism-ml | |||||
| PrismML: Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27b | Context window: 262,144Output limit: 32,768 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.50Cache read: 💵 $0.04 | Released, Last updated: 2026-09-18Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks... [{"type": "effort", "values": ["none", "medium", "xhigh"]}] |
| PrismML: Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9b | Context window: 262,144Output limit: 65,536 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.08Output: 💵 $0.13Cache read: 💵 $0.04 | Released, Last updated: 2026-10-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient... [{"type": "toggle"}] |
| qwen | |||||
| Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-prime | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $4.00Output: 💵 $12.00Cache read: 💵 $0.50 | Released, Last updated: 2026-09-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b | Context window: 1,048,576Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.25 | Released, Last updated: 2026-08-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is... [{"type": "effort", "values": ["low", "medium", "xhigh"]}] |
| Qwen: Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.25 | Released, Last updated: 2026-09-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,... [{"type": "effort", "values": ["minimal", "low", "medium", "high", "xhigh"]}] |
| Qwen: Qwen3.7 Maxqwen/qwen3.7-max | Context window: 1,000,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.48Output: 💵 $4.42Cache read: 💵 $0.30Cache write: 💵 $1.84 | Released, Last updated: 2026-05-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,... [{"type": "toggle"}] |
| Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Context window: 262,144Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.50Output: 💵 $3.60Cache read: 💵 $0.30 | Released, Last updated: 2026-02-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers... [{"type": "toggle"}] |
| Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | Context window: 128,000Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.45Output: 💵 $3.50 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-25Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144... |
| Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | Context window: 262,144Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.45Output: 💵 $2.70 | Released, Last updated: 2026-04-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs... [{"type": "toggle"}] |
| Qwen: Qwen3.5-27Bqwen/qwen3.5-27b | Context window: 262,144Output limit: 81,920 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.26Output: 💵 $2.60 | Released, Last updated: 2026-02-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of... [{"type": "toggle"}] |
| Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Context window: 262,144Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.26Output: 💵 $2.08 | Released, Last updated: 2026-02-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of... [{"type": "toggle"}] |
| Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.32Output: 💵 $1.95Cache write: 💵 $0.41 | Knowledge cutoff: 2025-04Released, Last updated: 2026-04-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers... [{"type": "toggle"}] |
| Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Context window: 262,144Output limit: 32,768 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.21Output: 💵 $1.90Cache read: 💵 $0.10 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-09-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table... |
| Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.30Output: 💵 $1.80Cache write: 💵 $0.38 | Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This... [{"type": "toggle"}] |
| Qwen: Qwen3.8 27Bqwen/qwen3.8-27b | Context window: 1,024,000Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $1.88Cache read: 💵 $0.04 | Released, Last updated: 2026-08-14Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be... [{"type": "effort", "values": ["none", "low", "medium", "xhigh"]}] |
| Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.26Output: 💵 $1.56 | Knowledge cutoff: 2025-04Released, Last updated: 2026-02-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of... [{"type": "toggle"}] |
| Qwen: Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct | Context window: 128,000Output limit: 115,200 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.80Output: 💵 $1.00Cache read: 💵 $0.40 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-01-26Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images. |
| Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct | Context window: 32,768Output limit: 29,491 | Input modalities, Output modalities: text | Input: 💵 $0.66Output: 💵 $1.00 | Knowledge cutoff: 2024-06-30Released, Last updated: 2024-11-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning... |
| Qwen: Qwen3.7 Plusqwen/qwen3.7-plus | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.32Output: 💵 $1.28Cache read: 💵 $0.06Cache write: 💵 $0.40 | Knowledge cutoff: 2025-04Released, Last updated: 2026-06-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its... [{"type": "toggle"}] |
| Qwen: Qwen3.6 Flashqwen/qwen3.6-flash | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.19Output: 💵 $1.12Cache write: 💵 $0.23 | Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in... [{"type": "toggle"}] |
| Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coder | Context window: 262,144Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $1.00Cache read: 💵 $0.10 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over... |
| Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking | Context window: 262,144Output limit: 235,929 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.29Output: 💵 $1.00 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-10-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels... |
| Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Context window: 262,144Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.09Output: 💵 $1.10 | Knowledge cutoff: 2025-09-30Released, Last updated: 2025-09Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual... |
| Qwen: Qwen3 Coder Flashqwen/qwen3-coder-flash | Context window: 1,000,000Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.20Output: 💵 $0.98Cache read: 💵 $0.04Cache write: 💵 $0.24 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling... |
| Qwen: Qwen3.7 Plus (batch)qwen/qwen3.7-plus:batch | Context window: 262,144 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.23Output: 💵 $0.92 | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its... | |
| Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Context window: 262,144Output limit: 81,920 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.14Output: 💵 $1.00Cache read: 💵 $0.05 | Released, Last updated: 2026-02-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall... [{"type": "toggle"}] |
| Qwen: Qwen-Plusqwen/qwen-plus | Context window: 1,000,000Output limit: 32,768 | Input modalities, Output modalities: text | Input: 💵 $0.26Output: 💵 $0.78Cache read: 💵 $0.05Cache write: 💵 $0.32 | Knowledge cutoff: 2025-03-31Released: 2024-01-25Last updated: 2025-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination. |
| Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | Context window: 262,144Output limit: 235,929 | Input modalities: image, textOutput modalities: text | Input: 💵 $0.25Output: 💵 $0.75Cache read: 💵 $0.12 | Released, Last updated: 2025-10-14Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon... |
| Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | Context window: 262,144Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.90Cache read: 💵 $0.02 | Released, Last updated: 2026-04-17Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated... [{"type": "toggle"}] |
| Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $0.80Cache read: 💵 $0.07 | Knowledge cutoff: 2025-09Released, Last updated: 2026-02-03Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per... |
| Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | Context window: 32,768Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.36Output: 💵 $0.40 | Knowledge cutoff: 2024-06-30Released, Last updated: 2024-09-19Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and... |
| Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct | Context window: 262,144Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.60 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-10-04Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception... |
| Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Context window: 262,144Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.09Output: 💵 $0.55 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,... |
| Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3b | Context window: 40,960Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $0.50 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-04-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique... [{"type": "toggle"}] |
| Qwen: Qwen3.8 Flashqwen/qwen3.8-flash | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.47Cache read: 💵 $0.02 | Released, Last updated: 2026-08-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis. [{"type": "toggle"}, {"type": "budget_tokens"}] |
| Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, audio, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.47Cache read: 💵 $0.02 | Released, Last updated: 2026-09-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,... [{"type": "toggle"}, {"type": "budget_tokens"}] |
| Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | Context window: 262,144Output limit: 235,929 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.17Output: 💵 $0.25 | Released, Last updated: 2026-02-23Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design... [{"type": "toggle"}] |
| Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input, Cache read: 💵 $0.10Output: 💵 $0.30 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and... |
| Qwen: Qwen3 32Bqwen/qwen3-32b | Context window: 131,072Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $0.28 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-04-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for... [{"type": "toggle"}] |
| Qwen: Qwen3 14Bqwen/qwen3-14b | Context window: 40,960Output limit: 16,384 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $0.24 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-04-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for... [{"type": "toggle"}] |
| Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.28 | Knowledge cutoff: 2025-06-30Released, Last updated: 2025-07-31Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the... |
| Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.06Output: 💵 $0.26 | Released, Last updated: 2026-02-25Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the... [{"type": "toggle"}] |
| Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | Context window: 32,768Output limit: 29,491 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.20 | Knowledge cutoff: 2024-06-30Released, Last updated: 2024-10-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and... |
| Qwen: Qwen3.7 Flashqwen/qwen3.7-flash | Context window: 1,000,000Output limit: 65,536 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.03Output: 💵 $0.13Cache read: 💵 $0.01Cache write: 💵 $0.04 | Released, Last updated: 2026-07-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world... [{"type": "toggle"}, {"type": "budget_tokens"}] |
| recursive | |||||
| Recursive: Flint (free)recursive/flint-v1.0:free | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-10-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited... |
| reflection | |||||
| Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | Context window: 1,048,576Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.25Output: 💵 $1.00Cache read: 💵 $0.05 | Knowledge cutoff: 2026-06-30Released: 2026-10-05Last updated: 2026-10-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a... [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| rekaai | |||||
| Reka Flash 3rekaai/reka-flash-3 | Context window: 65,536Output limit: 58,982 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.20 | Knowledge cutoff: 2025-01-31Released, Last updated: 2025-03-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a... |
| Reka Edgerekaai/reka-edge | Context window: 16,384Output limit: 14,745 | Input modalities: image, text, videoOutput modalities: text | Input, Output: 💵 $0.10 | Released, Last updated: 2026-03-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,... |
| relace | |||||
| Relace: Relace Searchrelace/relace-search | Context window: 256,000Output limit: 128,000 | Input modalities, Output modalities: text | Input: 💵 $1.00Output: 💵 $3.00 | Released, Last updated: 2025-12-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ The relace-search model uses 4-12 |
| Relace: Relace Apply 3relace/relace-apply-3 | Context window: 256,000Output limit: 128,000 | Input modalities, Output modalities: text | Input: 💵 $0.85Output: 💵 $1.25 | Released, Last updated: 2025-09-26Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at... |
| sakana | |||||
| Sakana: Fugu Ultrasakana/fugu-ultra | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, imageOutput modalities: text | Input: 💵 $5.00Output: 💵 $30.00Cache read: 💵 $0.50 | Released, Last updated: 2026-06-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route... [{"type": "effort", "values": ["high", "xhigh", "max"]}] |
| Sakana: Fugu Ultra v2sakana/fugu-ultra-v2 | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $5.00Output: 💵 $30.00Cache read: 💵 $0.50 | Knowledge cutoff: 2026-08-28Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to... [{"type": "effort", "values": ["high", "xhigh", "max"]}] |
| Sakana: Fugu Maxsakana/fugu-max | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.25 | Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route... [{"type": "effort", "values": ["high", "xhigh", "max"]}] |
| Sakana: Sakana Namazusakana/sakana-namazu | Context window: 262,144Output limit: 65,536 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.95Output: 💵 $4.00Cache read: 💵 $0.15 | Released, Last updated: 2026-08-03Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,... [{"type": "effort", "values": ["none", "high"]}] |
| sao10k | |||||
| Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b | Context window: 131,072Output limit: 16,384 | Input modalities, Output modalities: text | Input, Output: 💵 $0.85 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-08-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1. |
| Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | Context window: 8,192Output limit: 7,372 | Input modalities, Output modalities: text | Input: 💵 $0.04Output: 💵 $0.05 | Knowledge cutoff: 2023-12-31Released, Last updated: 2024-08-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge.... |
| scaledown | |||||
| ScaleDown: Extractscaledown/extract | Context window: 1,000,000Output limit: 900,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.04Output: 💵 $0.00 | Released, Last updated: 2026-10-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through |
| ScaleDown: Summarizescaledown/summarize | Context window: 1,000,000Output limit: 4,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.04Output: 💵 $0.00 | Released, Last updated: 2026-10-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for... |
| stepfun | |||||
| StepFun: Step 5 Previewstepfun/step-5-preview | Context window: 1,048,576Output limit: 64,000 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $1.00Output: 💵 $2.70Cache read: 💵 $0.10 | Released: 2026-09-16Last updated: 2026-09-20Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| StepFun: Step 3.7 Flashstepfun/step-3.7-flash | Context window: 262,144Output limit: 230,400 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.20Output: 💵 $1.15Cache read: 💵 $0.04 | Knowledge cutoff: 2026-03-01Released, Last updated: 2026-05-29Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters... [{"type": "effort", "values": ["low", "medium", "high"]}] |
| StepFun: Step 3.5 Flashstepfun/step-3.5-flash | Context window: 262,144Output limit: 65,536 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $0.30 | Knowledge cutoff: 2025-01Released: 2026-01-29Last updated: 2026-02-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token.... |
| tencent | |||||
| Tencent: Hy4 previewtencent/hy4-preview | Context window: 1,048,576Output limit: 64,000 | Input modalities, Output modalities: text | Input: 💵 $0.83Output: 💵 $2.50Cache read: 💵 $0.04 | Released, Last updated: 2026-08-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that... [{"type": "effort", "values": ["none", "low", "high"]}] |
| Tencent: Hy3 previewtencent/hy3-preview | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.18Output: 💵 $0.60Cache read: 💵 $0.06 | Released, Last updated: 2026-04-20Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to... [{"type": "effort", "values": ["none", "low", "high"]}] |
| Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $0.14Output: 💵 $0.57 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-07-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark... [{"type": "toggle"}] |
| Tencent: Hy3tencent/hy3 | Context window: 262,144Output limit: 128,000 | Input modalities, Output modalities: text | Input: 💵 $0.13Output: 💵 $0.53Cache read: 💵 $0.03 | Released, Last updated: 2026-07-06Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:... [{"type": "effort", "values": ["none", "low", "high"]}] |
| Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b | Context window: 8,192Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.30 | Released, Last updated: 2026-05-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and... |
| Tencent: Hy-MT2-7Btencent/hy-mt2-7b | Context window: 8,192Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.30 | Released, Last updated: 2026-05-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation. |
| Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b | Context window: 8,192Output limit: 4,096 | Input modalities, Output modalities: text | Input: 💵 $0.04Output: 💵 $0.18 | Released, Last updated: 2026-05-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided... |
| thedrummer | |||||
| TheDrummer: Skyfall 36B V2thedrummer/skyfall-36b-v2 | Context window: 32,768Output limit: 29,491 | Input modalities, Output modalities: text | Input: 💵 $0.55Output: 💵 $0.80Cache read: 💵 $0.25 | Knowledge cutoff: 2024-06-30Released, Last updated: 2025-03-10Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling. |
| TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1 | Context window: 131,072Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $0.30Output: 💵 $0.50Cache read: 💵 $0.15 | Knowledge cutoff: 2024-04-30Released, Last updated: 2025-09-27Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence. |
| TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b | Context window: 1,024,000Output limit: 819,200 | Input modalities, Output modalities: text | Input, Output: 💵 $0.40 | Knowledge cutoff: 2024-04-30Released, Last updated: 2024-11-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios. |
| thinkingmachines | |||||
| Thinking Machines: Inklingthinkingmachines/inkling | Context window: 524,288Output limit: 471,859 | Input modalities: text, image, audioOutput modalities: text | Input: 💵 $1.00Output: 💵 $4.05Cache read: 💵 $0.17 | Released, Last updated: 2026-07-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "max"]}] |
| Thinking Machines: Inkling Smallthinkingmachines/inkling-small | Context window: 524,288Output limit: 262,144 | Input modalities: text, image, audioOutput modalities: text | Input: 💵 $0.45Output: 💵 $1.20Cache read: 💵 $0.10 | Released, Last updated: 2026-07-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "max"]}] |
| Thinking Machines: Inkling Small (free)thinkingmachines/inkling-small:free | Context window: 1,048,576Output limit: 262,144 | Input modalities: text, image, audioOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-07-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "max"]}] |
| Thinking Machines: Inkling (free)thinkingmachines/inkling:free | Context window: 1,048,576Output limit: 262,144 | Input modalities: text, image, audioOutput modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-07-15Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "max"]}] |
| typesafe | |||||
| TypeSafe: Jev Routertypesafe/jev-router | Context window: 1,000,000 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input, Output: 💵 -$1,000,000.00 | 💬🖼️🔧🧠📋🔊📎🌡️ Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System One model, and adapts as your... | |
| unbiased | |||||
| Pareto 26.9unbiased/pareto-26.9 | Context window: 262,144Output limit: 131,072 | Input modalities: text, imageOutput modalities: text | Input: 💵 $2.50Output: 💵 $7.50Cache read: 💵 $0.25 | Released, Last updated: 2026-10-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. |
| Pareto 26.10unbiased/pareto-26.10 | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.80Output: 💵 $3.20Cache read: 💵 $0.03 | Released, Last updated: 2026-10-15Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. |
| undi95 | |||||
| ReMM SLERP 13Bundi95/remm-slerp-l2-13b | Context window: 6,144Output limit: 5,529 | Input modalities, Output modalities: text | Input: 💵 $0.35Output: 💵 $0.65 | Knowledge cutoff: 2023-06-30Released, Last updated: 2023-07-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge |
| upstage | |||||
| Upstage: Solar Pro 4upstage/solar-pro4 | Context window: 524,288Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.15Output: 💵 $0.60Cache read: 💵 $0.03 | Knowledge cutoff: 2026-02Released, Last updated: 2026-08-06Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"]}] |
| Upstage: Solar Mini 4upstage/solar-mini4 | Context window: 524,288Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.05Output: 💵 $0.20Cache read: 💵 $0.00 | Knowledge cutoff: 2026-02Released, Last updated: 2026-09-22Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response... [{"type": "effort", "values": ["none", "minimal", "low", "medium", "high", "xhigh", "max"]}] |
| writer | |||||
| Writer: Palmyra X5writer/palmyra-x5 | Context window: 1,040,000Output limit: 8,192 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $6.00 | Released, Last updated: 2025-04-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million... |
| x-ai | |||||
| SpaceXAI: Grok 4.5x-ai/grok-4.5 | Context window: 500,000Output limit: 450,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.30 | Released, Last updated: 2026-07-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. [{"type": "effort", "values": ["low", "medium", "high"]}] |
| SpaceXAI: Grok 4.6x-ai/grok-4.6 | Context window: 500,000Output limit: 450,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.50 | Knowledge cutoff: 2026-02-01Released, Last updated: 2026-08-12Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7. [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| SpaceXAI: Grok 4.7x-ai/grok-4.7 | Context window: 500,000Output limit: 450,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.50 | Knowledge cutoff: 2026-05Released, Last updated: 2026-09-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| SpaceXAI: Grok 4.20x-ai/grok-4.20 | Context window: 2,000,000Output limit: 1,800,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Knowledge cutoff: 2025-09-01Released, Last updated: 2026-03-31Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering... [{"type": "toggle"}] |
| SpaceXAI: Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent | Context window: 2,000,000Output limit: 1,800,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Knowledge cutoff: 2025-09-01Released, Last updated: 2026-03-31Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information... [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| SpaceXAI: Grok 4.3x-ai/grok-4.3 | Context window: 1,000,000Output limit: 900,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Released, Last updated: 2026-04-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual... [{"type": "effort", "values": ["none", "low", "medium", "high"]}] |
| SpaceXAI: Grok 4.3 (batch)x-ai/grok-4.3:batch | Context window: 1,000,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $2.00Cache read: 💵 $0.16 | 💬🖼️🔧🧠📋🔊📎🌡️ Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual... | |
| SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1 | Context window: 256,000Output limit: 230,400 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $1.00Output: 💵 $2.00Cache read: 💵 $0.20 | Released, Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding... |
| xiaomi | |||||
| Xiaomi: MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, image, video, audioOutput modalities: text | Input: 💵 $4.35Output: 💵 $8.70Cache read: 💵 $0.04 | Released, Last updated: 2026-09-21Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x... [{"type": "toggle"}] |
| Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5 | Context window: 1,050,000Output limit: 65,536 | Input modalities: text, audio, image, videoOutput modalities: text | Input: 💵 $0.40Output: 💵 $2.00Cache read: 💵 $0.08 | Knowledge cutoff: 2024-12Released, Last updated: 2026-04-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding... [{"type": "toggle"}] |
| Xiaomi: MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Context window: 1,050,000Output limit: 235,929 | Input modalities, Output modalities: text | Input: 💵 $0.48Output: 💵 $1.80Cache read: 💵 $0.10 | Knowledge cutoff: 2024-12Released, Last updated: 2026-04-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.... [{"type": "toggle"}] |
| Xiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | Context window: 1,050,000Output limit: 131,072 | Input modalities: text, image, video, audioOutput modalities: text | Input: 💵 $0.44Output: 💵 $0.87Cache read: 💵 $0.004 | Released, Last updated: 2026-09-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding... [{"type": "toggle"}] |
| Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Context window: 1,050,000Output limit: 131,072 | Input modalities: text, image, video, audioOutput modalities: text | Input: 💵 $0.14Output: 💵 $0.28Cache read: 💵 $0.003 | Released, Last updated: 2026-09-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for... [{"type": "toggle"}] |
| xingchen-agi | |||||
| XingChen: Xing4.0 29B A4B (free)xingchen-agi/xing4.0-29b-a4b:free | Context window: 262,144Output limit: 235,929 | Input modalities, Output modalities: text | Input, Output: 💵 $0.00 | Released, Last updated: 2026-10-16Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token... [{"type": "toggle"}] |
| z-ai | |||||
| Z.ai: GLM 5.3 Primez-ai/glm-5.3-prime | Context window: 1,000,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $2.80Output: 💵 $8.80Cache read: 💵 $0.56 | Released, Last updated: 2026-09-23Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token... [{"type": "effort", "values": ["low", "high", "max"]}] |
| Z.ai: GLM 5.2z-ai/glm-5.2 | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.01Output: 💵 $6.80Cache read: 💵 $0.00 | Released, Last updated: 2026-06-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,... [{"type": "effort", "values": ["none", "high", "xhigh"]}] |
| Z.ai: GLM 5.1z-ai/glm-5.1 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.40Output: 💵 $4.40Cache read: 💵 $0.26 | Released, Last updated: 2026-04-07Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on... [{"type": "toggle"}] |
| Z.ai: GLM 5 Turboz-ai/glm-5-turbo | Context window: 202,752Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.20Output: 💵 $4.00Cache read: 💵 $0.24 | Released, Last updated: 2026-03-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows... [{"type": "toggle"}] |
| Z.ai: GLM 5V Turboz-ai/glm-5v-turbo | Context window: 202,752Output limit: 131,072 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $1.20Output: 💵 $4.00Cache read: 💵 $0.24 | Released, Last updated: 2026-04-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,... [{"type": "toggle"}] |
| Z.ai: GLM 5z-ai/glm-5 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.00Output: 💵 $3.20Cache read: 💵 $0.20 | Released, Last updated: 2026-02-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading... [{"type": "toggle"}] |
| Z.ai: GLM 5.3z-ai/glm-5.3 | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.08Output: 💵 $3.60Cache read: 💵 $0.08 | Released, Last updated: 2026-08-14Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves... [{"type": "effort", "values": ["low", "high", "max"]}] |
| Z.ai: GLM 4.5z-ai/glm-4.5 | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.20Cache read: 💵 $0.11 | Knowledge cutoff: 2024-12-31Released, Last updated: 2025-07-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly... [{"type": "toggle"}] |
| Z.ai: GLM 4.7z-ai/glm-4.7 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.20Cache read: 💵 $0.11 | Knowledge cutoff: 2025-04Released, Last updated: 2025-12-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while... [{"type": "toggle"}] |
| Z.ai: GLM 4.6z-ai/glm-4.6 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.50Output: 💵 $2.00Cache read: 💵 $0.10 | Knowledge cutoff: 2025-03-31Released, Last updated: 2025-09-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex... [{"type": "toggle"}] |
| Z.ai: GLM 5.3 (batch)z-ai/glm-5.3:batch | Context window: 1,048,576 | Input modalities, Output modalities: text | Input: 💵 $0.45Output: 💵 $2.00Cache read: 💵 $0.10 | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves... | |
| Z.ai: GLM 4.5Vz-ai/glm-4.5v | Context window: 65,536Output limit: 16,384 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.60Output: 💵 $1.80Cache read: 💵 $0.11 | Knowledge cutoff: 2024-12-31Released, Last updated: 2025-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,... [{"type": "toggle"}] |
| Z.ai: GLM 5.3 FlashXz-ai/glm-5.3-flashx | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.37Output: 💵 $1.25Cache read: 💵 $0.08 | Released, Last updated: 2026-09-18Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture... [{"type": "effort", "values": ["low", "high", "max"]}] |
| Z.ai: GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.37Output: 💵 $1.25Cache read: 💵 $0.08 | Released, Last updated: 2026-11-02Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement... [{"type": "effort", "values": ["low", "high", "max"]}] |
| Z.ai: GLM 4.6Vz-ai/glm-4.6v | Context window: 131,072Output limit: 32,768 | Input modalities: image, text, videoOutput modalities: text | Input: 💵 $0.30Output: 💵 $0.90Cache read: 💵 $0.06 | Knowledge cutoff: 2025-04Released, Last updated: 2025-12-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts... [{"type": "toggle"}] |
| Z.ai: GLM 4.5 Airz-ai/glm-4.5-air | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.13Output: 💵 $0.85Cache read: 💵 $0.02 | Knowledge cutoff: 2024-12-31Released, Last updated: 2025-07-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter... [{"type": "toggle"}] |
| Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash | Context window: 200,000Output limit: 117,964 | Input modalities, Output modalities: text | Input: 💵 $0.06Output: 💵 $0.40 | Knowledge cutoff: 2025-04Released, Last updated: 2026-01-19Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,... [{"type": "toggle"}] |
| Z.ai: GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batch | Context window: 1,048,576 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.05Output: 💵 $0.18Cache read: 💵 $0.01 | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while... | |
| Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input, Cache read: 💵 $0.03Output: 💵 $0.09 | Released, Last updated: 2026-08-26Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while... [{"type": "effort", "values": ["low", "high", "max"]}] |
| ~anthropic | |||||
| Anthropic: Claude Fable Latest~anthropic/claude-fable-latest | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $0.25Cache write: 💵 $12.50 | Released, Last updated: 2026-06-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Claude Fable family. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Opus Latest~anthropic/claude-opus-latest | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $4.00Output: 💵 $20.00Cache read: 💵 $0.20Cache write: 💵 $5.00 | Released, Last updated: 2026-04-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Claude Opus family. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Sonnet Latest~anthropic/claude-sonnet-latest | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-01-31Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Claude Sonnet family. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| Anthropic: Claude Haiku Latest~anthropic/claude-haiku-latest | Context window: 1,000,000Output limit: 128,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Claude Haiku family. [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| ~deepseek | |||||
| DeepSeek: DeepSeek Pro Latest~deepseek/deepseek-pro-latest | Context window: 1,048,576Output limit: 393,216 | Input modalities, Output modalities: text | Input: 💵 $0.10Output: 💵 $8.00Cache read: 💵 $0.10 | Released, Last updated: 2026-09-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the DeepSeek Pro family. [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek Flash Latest~deepseek/deepseek-flash-latest | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.04Output: 💵 $0.50Cache read: 💵 $0.00 | Released, Last updated: 2026-09-14Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the DeepSeek Flash family. [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.06Output: 💵 $0.30Cache read: 💵 $0.04 | Released, Last updated: 2026-08-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the DeepSeek V4 Flash family. [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| Google: Gemini Pro Latest~google/gemini-pro-latest | Context window: 1,048,576Output limit: 943,718 | Input modalities: audio, file, image, text, videoOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $0.19 | Knowledge cutoff: 2025-01Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Gemini Pro family. [{"type": "effort", "values": ["low", "medium", "high"]}] |
| Google: Gemini Flash Latest~google/gemini-flash-latest | Context window: 1,048,576Output limit: 65,536 | Input modalities: text, image, video, file, audioOutput modalities: text | Input: 💵 $0.75Output: 💵 $3.75Cache read: 💵 $0.08Cache write: 💵 $0.04 | Knowledge cutoff: 2025-01-01Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Gemini Flash family. [{"type": "effort", "values": ["low", "medium", "high"]}] |
| ~moonshotai | |||||
| MoonshotAI: Kimi Latest~moonshotai/kimi-latest | Context window: 1,048,576Output limit: 943,718 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $7.15Cache read: 💵 $0.08 | Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Kimi family. [{"type": "effort", "values": ["none", "low", "high", "max"]}] |
| ~openai | |||||
| OpenAI: GPT Astra Latest~openai/gpt-astra-latest | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $10.00Output: 💵 $50.00Cache read: 💵 $1.00Cache write: 💵 $12.50 | Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GPT Astra family. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT Sol Latest~openai/gpt-sol-latest | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $2.00Output: 💵 $10.00Cache read: 💵 $0.10Cache write: 💵 $2.50 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GPT Sol family. [{"type": "effort", "values": ["low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT Terra Latest~openai/gpt-terra-latest | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $1.00Output: 💵 $5.00Cache read: 💵 $0.05Cache write: 💵 $1.25 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GPT Terra family. [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| OpenAI: GPT Mini Latest~openai/gpt-mini-latest | Context window: 400,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.75Output: 💵 $4.50Cache read: 💵 $0.08 | Knowledge cutoff: 2025-08-31Released, Last updated: 2026-04-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GPT Mini family. [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| OpenAI: GPT Luna Latest~openai/gpt-luna-latest | Context window: 1,050,000Output limit: 128,000 | Input modalities: file, image, textOutput modalities: text | Input: 💵 $0.10Output: 💵 $0.50Cache read: 💵 $0.01Cache write: 💵 $0.12 | Knowledge cutoff: 2026-02-16Released, Last updated: 2026-09-11Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GPT Luna family. [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh", "max"]}] |
| ~unbiased | |||||
| Pareto Latest~unbiased/pareto-latest | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, imageOutput modalities: text | Input: 💵 $0.80Output: 💵 $3.20Cache read: 💵 $0.03 | Released, Last updated: 2026-10-13Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the Pareto family. |
| ~x-ai | |||||
| xAI: Grok Latest~x-ai/grok-latest | Context window: 500,000Output limit: 450,000 | Input modalities: text, image, fileOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.50 | Released, Last updated: 2026-07-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest Grok model from xAI. [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| ~z-ai | |||||
| Z.ai: GLM Latest~z-ai/glm-latest | Context window: 1,048,576Output limit: 943,718 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $1.40Cache read: 💵 $0.07 | Released, Last updated: 2026-08-19Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest GLM model from Z.ai. [{"type": "effort", "values": ["low", "high", "max"]}] |
| Z.ai: GLM Flash Latest~z-ai/glm-flash-latest | Context window: 1,048,576Output limit: 131,072 | Input modalities: text, image, videoOutput modalities: text | Input, Cache read: 💵 $0.03Output: 💵 $0.09 | Released, Last updated: 2026-08-27Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ This model always redirects to the latest model in the GLM Flash family. [{"type": "effort", "values": ["low", "high", "max"]}] |
xAI (Grok) 8
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| Grok 4.5grok-4.5 | Context window, Output limit: 500,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.30 | Released, Last updated: 2026-07-08Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Grok 4.6grok-4.6 | Context window, Output limit: 500,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.50 | Knowledge cutoff: 2026-02-01Released, Last updated: 2026-08-12Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ xAI's frontier model for long-running agents, coding, knowledge work, and visual projects [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Grok 4.7grok-4.7 | Context window, Output limit: 500,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $2.00Output: 💵 $6.00Cache read: 💵 $0.50 | Knowledge cutoff: 2026-05Released, Last updated: 2026-09-21Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ xAI's frontier model for long-running agents, coding, knowledge work, and visual projects [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Grok 4.20 (Non-Reasoning)grok-4.20-0309-non-reasoning | Context window: 1,000,000Output limit: 30,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Released, Last updated: 2026-03-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok model for agentic tool use, reasoning, coding, and live assistance |
| Grok 4.20 (Reasoning)grok-4.20-0309-reasoning | Context window: 1,000,000Output limit: 30,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Released, Last updated: 2026-03-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Reasoning Grok for document-heavy analysis and long-horizon tool use |
| Grok 4.20 Multi-Agentgrok-4.20-multi-agent-0309 | Context window: 1,000,000Output limit: 30,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Released, Last updated: 2026-03-09Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Grok model for agentic tool use, reasoning, coding, and live assistance [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}] |
| Grok 4.3grok-4.3 | Context window: 1,000,000Output limit: 30,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.25Output: 💵 $2.50Cache read: 💵 $0.20 | Released, Last updated: 2026-04-17Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ xAI's Grok for chat, coding, agentic tools, and lower hallucination risk [{"type": "effort", "values": ["none", "low", "medium", "high", "xhigh"]}] |
| Grok Build 0.1grok-build-0.1 | Context window, Output limit: 256,000 | Input modalities: text, image, pdfOutput modalities: text | Input: 💵 $1.00Output: 💵 $2.00Cache read: 💵 $0.20 | Released, Last updated: 2026-04-16Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast Grok coding model tuned for agentic engineering and iterative edits |
z.ai 17
| Model | Limits | Modalities | Cost / 1M | Details | Capabilities |
|---|---|---|---|---|---|
| GLM-5.2glm-5.2 | Context window: 1,000,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.20Output: 💵 $4.18Cache read: 💵 $0.30Cache write: 💵 $0.00 | Released, Last updated: 2026-06-13Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Open flagship GLM for long-horizon coding agents and million-token context work [{"type": "toggle"}, {"type": "effort", "values": ["high", "max"]}] |
| GLM-5.3glm-5.3 | Context window: 1,000,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $1.20Output: 💵 $4.18Cache read: 💵 $0.30Cache write: 💵 $0.00 | Released, Last updated: 2026-08-14Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Flagship GLM model for long-horizon coding, agents, and complex project delivery [{"type": "effort", "values": ["low", "high", "max"]}] |
| GLM-5.1glm-5.1 | Context window: 200,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.90Output: 💵 $3.59Cache read: 💵 $0.19Cache write: 💵 $0.00 | Released, Last updated: 2026-04-07Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Strong GLM coding model for agentic engineering, terminals, and repository generation [{"type": "toggle"}] |
| GLM-5V-Turboglm-5v-turbo | Context window: 200,000Output limit: 131,072 | Input modalities: text, image, video, pdfOutput modalities: text | Input: 💵 $0.75Output: 💵 $3.29Cache read: 💵 $0.18Cache write: 💵 $0.00 | Released, Last updated: 2026-04-01Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Fast GLM vision model for screenshots, documents, and multimodal agent tasks [{"type": "toggle"}] |
| GLM-5glm-5 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.69Cache read: 💵 $0.15Cache write: 💵 $0.00 | Released, Last updated: 2026-02-12Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ General GLM flagship for coding, analysis, and tool-heavy engineering workflows [{"type": "toggle"}] |
| GLM-4.5glm-4.5 | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.20Cache read: 💵 $0.11Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-07-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Hybrid-reasoning GLM release that made the 4.5 line broadly useful [{"type": "toggle"}] |
| GLM-4.6glm-4.6 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.60Output: 💵 $2.20Cache read: 💵 $0.11Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-09-30Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Late GLM-4 workhorse for coding agents, reasoning, and structured tasks [{"type": "toggle"}] |
| GLM-4.7glm-4.7 | Context window: 204,800Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.45Output: 💵 $2.09Cache read: 💵 $0.09Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-12-22Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Mature GLM model for dependable coding, reasoning, and structured agent tasks [{"type": "toggle"}] |
| GLM-5.3-FlashXglm-5.3-flashx | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, video, pdfOutput modalities: text | Input: 💵 $0.30Output: 💵 $1.05Cache read: 💵 $0.09Cache write: 💵 $0.00 | Released, Last updated: 2026-09-18Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ High-speed GLM-5.3-Flash serving option for coding and agent workflows [{"type": "effort", "values": ["low", "high", "max"]}] |
| GLM-4.5Vglm-4.5v | Context window: 64,000Output limit: 16,384 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.30Output: 💵 $0.90Cache read: 💵 $0.06Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-08-11Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM vision model for visual reasoning, documents, and multimodal agents [{"type": "toggle"}] |
| GLM-4.5-Airglm-4.5-air | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input: 💵 $0.12Output: 💵 $0.90Cache read: 💵 $0.02Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-07-28Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Lighter GLM-4.5 variant for fast coding assistance and cheaper agents [{"type": "toggle"}] |
| GLM-4.6Vglm-4.6v | Context window: 128,000Output limit: 32,768 | Input modalities: text, image, videoOutput modalities: text | Input: 💵 $0.15Output: 💵 $0.45Cache read: 💵 $0.03Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-12-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ GLM vision model for visual reasoning, documents, and multimodal agents [{"type": "toggle"}] |
| GLM-5.3-Flashglm-5.3-flash | Context window: 1,000,000Output limit: 131,072 | Input modalities: text, image, video, pdfOutput modalities: text | Input: 💵 $0.12Output: 💵 $0.42Cache read: 💵 $0.03Cache write: 💵 $0.00 | Released, Last updated: 2026-08-26Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Native multimodal GLM model for efficient coding and long-horizon agent tasks [{"type": "effort", "values": ["low", "high", "max"]}] |
| GLM-4.7-FlashXglm-4.7-flashx | Context window: 200,000Output limit: 131,072 | Input modalities, Output modalities: text | Input: 💵 $0.07Output: 💵 $0.45Cache read: 💵 $0.01Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2026-01-19Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Efficient GLM model for fast reasoning, coding, and agent workflows [{"type": "toggle"}] |
| GLM-4.5-Flashglm-4.5-flash | Context window: 131,072Output limit: 98,304 | Input modalities, Output modalities: text | Input, Output, Cache read, Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2025-07-28Open weights: ✗ | 💬🖼️🔧🧠📋🔊📎🌡️ Efficient GLM model for fast reasoning, coding, and agent workflows [{"type": "toggle"}] |
| GLM-4.6V-Flashglm-4.6v-flash | Context window: 128,000Output limit: 32,768 | Input modalities: text, image, videoOutput modalities: text | Input, Output, Cache read, Cache write: 💵 $0.00 | Released, Last updated: 2025-12-08Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Lightweight GLM vision model for visual reasoning, documents, and multimodal agents [{"type": "toggle"}] |
| GLM-4.7-Flashglm-4.7-flash | Context window: 200,000Output limit: 131,072 | Input modalities, Output modalities: text | Input, Output, Cache read, Cache write: 💵 $0.00 | Knowledge cutoff: 2025-04Released, Last updated: 2026-01-19Open weights: ✓ | 💬🖼️🔧🧠📋🔊📎🌡️ Budget GLM lane for fast coding help, routing, and everyday automation [{"type": "toggle"}] |