Mistral Large 4
Mistral Large 4 is a large language model made by Mistral, added to the catalog on 6 Oct 2026. It has a context window of 1,048,576 tokens and costs $0.70 per 1M input tokens and $2.10 per 1M output tokens. It accepts text and images and produces text. Typical uses: reasoning over text and image inputs, coding tasks with tool support and structured text generation.
Price checked ยท source: OpenRouter
What Mistral Large 4 is
Mistral Large 4 is a multimodal model from Mistral AI for reasoning, coding, and agentic workloads. It accepts text and image inputs and produces text. Its context window holds up to 1,048,576 tokens, and its maximum output is 262,144 tokens. This capacity suits requests that provide extensive context or call for lengthy text responses. It can combine text and image input in a workflow, with text as the stated output modality.
The model supports tools, structured outputs, response formats, and reasoning. Those features are relevant to tasks involving analysis, coding, tool use, or text that must follow a specified format. Its broad context window allows a request to include a large amount of material, so it may suit work drawing on lengthy prompts or multiple supplied items. Image input extends these workflows beyond text-only prompts, while the model still returns text rather than a generated image. The listed capabilities describe general support rather than a particular tool set, coding language, or image operation. Mistral Large 4's stated uses therefore center on text-based reasoning and coding, with image inputs and tool-enabled workflows available where relevant. The maximum-output limit sets a separate stated ceiling for generated text; it does not mean every request needs or produces a response at that length.
Key features
- Accepts text and image inputs and produces text
- Has a context window of 1,048,576 tokens
- Supports tool use and reasoning
- Supports structured outputs and response formats
- Maximum output is 262,144 tokens
Typical uses
- Reasoning over text and image inputs
- Coding tasks with tool support
- Structured text generation
- Long-context analysis
- Agentic workflows using tools
Mistral Large 4 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.70 |
| Output, per 1M tokens | $2.10 |
| Cached input read, per 1M tokens | $0.07 |
No price change since it was added on 6 Oct 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.019 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.025 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.108 |
Mistral Large 4 specifications
| Model id | mistralai/mistral-large-4-0 |
|---|---|
| Version | mistral-large-4-0-20261006 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 262,144 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 6 Oct 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Mistral Large 4 yet.
Compare Mistral Large 4
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.