Mistral / mistral/mistral-large-4
Mistral Large 4 - access through LLMTR
Mistral Large 4 is Mistral's open-weight model that combines instruction following, reasoning and tool-using agent work in one model, with text and image input. It offers a 524,288-token context window, up to 262,144 output tokens per response, tool calling, JSON mode and JSON Schema output, and automatic prompt caching with a lower rate for cached input. It reasons before answering by default and reasoning tokens are billed as output: send `reasoning_effort: "none"` for short, cheap answers or `"high"` for hard problems. Those are the two levels it accepts. To force a tool call, name the function in `tool_choice`; `"required"` is not available on this model. Mistral positions it for cybersecurity, finance and manufacturing work.
Technical specifications
| Canonical ID | mistral/mistral-large-4 |
|---|---|
| Provider | Mistral |
| Context window | 524,288 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.680000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.070000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $2.09 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"mistral/mistral-large-4","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Mistral Large 4 API: OpenAI SDK usage and pricing - On LLMTR, mistral/mistral-large-4 is called with the OpenAI SDK at https://llmtr.com/v1/chat/completions. It offers a 524,288-token context and up to 262,144 output tokens per response. Per 1M tokens it costs $0.68 input / $2.09 output until 20 October 2026, 00:00 UTC, and $1.36 / $4.18 from then on.
- A tool-calling agent with Mistral Large 4: tool_choice and reasoning - Mistral Large 4 calls tools on LLMTR through /v1/chat/completions. For tool_choice, auto, none and a named function work; required returns 400. In a multi-turn loop, assistant messages go back with reasoning_content, and that trace is billed as input tokens.
- Mistral Large 4 or Large 3? Context, reasoning and price - On LLMTR both models are called through /v1/chat/completions with the same API key. Large 4 offers a 524,288-token context and Large 3 256,000; Large 4 reasons by default and accepts the none and high levels. The mistral/mistral-large-latest id is pinned to Large 3 and does not move to Large 4 on its own.
Related models
- Mistral Large 3 mistral/mistral-large-latest
- Mistral Small 4 mistral/mistral-small-latest
- Mistral Medium 3.1 mistral/mistral-medium-latest
- Devstral 2 mistral/devstral-medium-latest
- Magistral Medium 1.2 mistral/magistral-medium-latest
- Magistral Small 1.2 mistral/magistral-small-latest
- Devstral Small 2 mistral/devstral-small-latest
- Codestral mistral/codestral-latest