Mistral Medium 3.5
Mistral Medium 3.5 is a large language model made by Mistral, added to the catalog on 30 Apr 2026. It has a context window of 262,144 tokens and costs $1.50 per 1M input tokens and $7.50 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: coding tasks, tool-assisted workflows and working with image and text inputs.
Price checked · source: OpenRouter
What Mistral Medium 3.5 is
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It accepts text, images, and files, and produces text. Its stated design includes agentic workflows and coding. The model supports several kinds of input while returning responses in text, and its catalog lists support for tools, structured outputs, response formats, and reasoning.
The context window is 262,144 tokens, and the maximum output is 209,715 tokens. These limits allow the model to work with substantial supplied context and produce long text responses, subject to the limits of the system using it. Text, image, and file inputs can be used as part of a task, while the output modality is text. The listed support for tools and structured outputs can be relevant when an application needs those options; response formatting and reasoning are also supported.
The model’s stated focus on coding and agentic workflows makes it suitable for coding tasks and tool-assisted processes. Its input options also suit work involving written material, images, or files that need a text response. The large context window is relevant to tasks that involve extensive supplied material, while structured outputs and response formats can be used when a response needs a specified structure. The catalog does not specify particular file formats or further details about its capabilities, so those should not be assumed.
Key features
- Accepts text, image, and file inputs
- Produces text output
- Has a 262,144-token context window
- Supports tools, structured outputs, response formats, and reasoning
- Maximum output is 209,715 tokens
Typical uses
- Coding tasks
- Tool-assisted workflows
- Working with image and text inputs
- Processing long supplied context
- Generating structured text
Mistral Medium 3.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $1.50 | $0.75 |
| Output, per 1M tokens | $7.50 | $3.75 |
| Variant | Model id |
|---|---|
| Batch | mistralai/mistral-medium-3-5:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 30 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0030 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.044 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.060 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.236 |
Mistral Medium 3.5 specifications
| Model id | mistralai/mistral-medium-3-5 |
|---|---|
| Version | mistral-medium-3.5-20260430 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 209,715 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 30 Apr 2026 |
| Input types | text, image, file |
|---|---|
| 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 Medium 3.5 yet.
Compare Mistral Medium 3.5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.