Using the LLM API
Models
Get a comprehensive overview of the supported models, context length, and pricing for the LLM relay.
Available models
| Model | Developer | Context Length | Knowledge cutoff | Input (per million tokens) | Output (per million tokens) |
|---|---|---|---|---|---|
| GPT-5.1 | OpenAI | 400,000 | Sep 30, 2024 | $1.25 | $10.00 |
| GPT-5 | OpenAI | 400,000 | Oct 01, 2024 | $1.25 | $10.00 |
| GPT-5 Mini | OpenAI | 400,000 | May 31, 2024 | $0.25 | $2.00 |
| GPT-5 Nano | OpenAI | 400,000 | May 31, 2024 | $0.05 | $0.40 |
| GPT-4.1 | OpenAI | 1 million | June 01, 2024 | $2.00 | $8.00 |
| GPT-4.1 Mini | OpenAI | 1 million | June 01, 2024 | $0.40 | $1.60 |
| GPT-4.1 Nano | OpenAI | 1 million | June 01, 2024 | $0.10 | $0.40 |
| GPT-4.5 Preview | OpenAI | 128,000 | Oct 01, 2023 | $75.00 | $150.00 |
| GPT-4o | OpenAI | 128,000 | Oct 01, 2023 | $2.50 | $10.00 |
| GPT-4o Mini | OpenAI | 128,000 | Oct 01, 2023 | $0.15 | $0.60 |
| o4-mini | OpenAI | 200,000 | Jun 01, 2024 | $1.10 | $4.40 |
| o3-mini | OpenAI | 200,000 | Oct 01, 2023 | $1.10 | $4.40 |
| o1 | OpenAI | 200,000 | Oct 01, 2023 | $15.00 | $60.00 |
| o1-mini | OpenAI | 128,000 | Oct 01, 2023 | $1.10 | $4.40 |
| DeepSeek Chat (DeepSeek-V3) | DeepSeek | 64,000 | Unknown | $0.27 | $1.10 |
| DeepSeek Reasoner (DeepSeek-R1) | DeepSeek | 64,000 | Unknown | $0.55 | $2.19 |
| Claude Opus 4.5 | Anthropic | 200,000 | Aug 2025 | $5.00 Caching write: $6.25 Caching read: $0.50 / MTok | $75.00 |
| Claude Opus 4.1 | Anthropic | 200,000 | Mar 2025 | $15.00 Caching write: $18.75 Caching read: $1.50 / MTok | $75.00 |
| Claude Opus 4 | Anthropic | 200,000 | Mar 2025 | $15.00 Caching write: $18.75 Caching read: $1.50 / MTok | $75.00 |
| Claude 3 Opus | Anthropic | 200,000 | Aug 2023 | $15.00 Caching write: $18.75 Caching read: $1.50 / MTok | $75.00 |
| Claude Sonnet 4.5 | Anthropic | 200,000 | Jul 2025 | $3.00 Caching write: $3.75 Caching read: $0.30 / MTok | $15.00 |
| Claude Sonnet 4 | Anthropic | 200,000 | Mar 2025 | $3.00 Caching write: $3.75 Caching read: $0.30 | $15.00 |
| Claude 3.7 Sonnet | Anthropic | 200,000 | Oct 2024 | $3.00 Caching write: $3.75 Caching read: $0.30 | $15.00 |
| Claude Haiku 4.5 | Anthropic | 200,000 | Jul 2024 | $1.00 Caching write: $1.25 Caching read: $0.10 | $5.00 |
| Claude 3.5 Haiku | Anthropic | 200,000 | July 2024 | $0.80 Caching write: $18.75 Caching read: $1.50 | $4.00 |
| Claude 3 Haiku | Anthropic | 200,000 | Aug 2023 | $0.25 Caching write: $0.30 Caching read: $0.03 | $1.25 |
| Gemini 3 Pro Preview | 1 million | Jan 2025 | $2.00 | $12.00 | |
| Gemini 2.5 Pro Preview | 1 million | Jan 2025 | $1.25 | $10.00 | |
| Gemini 1.5 Pro | 2 million | May 2024 | $1.25 | $5.00 | |
| Gemini 2.5 Flash Preview | 1 million | Jan 2025 | $0.15 | $0.60 | |
| Gemini 2.0 Flash | 1 million | August 2024 | $0.10 | $0.40 | |
| Gemini 2.0 Flash-Lite | 1 million | June 2024 | $0.075 | $0.30 | |
| Gemini 1.5 Flash | 1 million | Unknown | $0.075 | $0.30 | |
| Gemini 1.5 Flash-8B | 1 million | Unknown | $0.0375 | $0.15 | |
| Mistral NeMo | Mistral AI | 128,000 | Unknown | $0.035 | $0.08 |
| Llama 4 Maverick | Meta | 10 million | Aug 2024 | $0.17 | $0.85 |
| Llama 4 Scout | Meta | 1 million | Aug 2024 | $0.08 | $0.30 |
| Llama 3.3 | Meta | 200,000 | Dec 2023 | $0.12 | $0.30 |