Mistral · Model
Mistral Medium 3.5 pricing, context window and specs
Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens, and reads up to 262,144 tokens per request. By blended price it is the most expensive of Mistral’s 8 current models here.
- Input / 1M
- $1.50
- Output / 1M
- $7.50
- Cached / 1M
- –
- Context
- 262,144
- Max output
- Not published
- Released
- 2026-04-30
Estimate your cost with Mistral Medium 3.5Compare all Mistral modelsCount tokens for Mistral Medium 3.5
Pricing
Mistral Medium 3.5 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $1.50 | $7.50 |
| Batch API | $0.75 | $3.75 |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. No cached-input price is published, so repeated prompt prefixes are billed at the full input price.
Examples
What Mistral Medium 3.5 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot | 1,500 / 400 | 1,000 | $0.00525 | $159.69 |
| RAG app | 6,000 / 500 | 500 | $0.0128 | $193.91 |
| Coding agent | 40,000 / 2,000 | 200 | $0.075 | $456.25 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.00825 | $75.28 |
Change any number in the cost calculator.
Context
Context window
Mistral Medium 3.5 accepts up to 262,144 tokens per request, roughly 196,608 English words or 393 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.39 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- No
- Structured output
- Yes
- Open weights
- No
- Accepts
- text, image, file
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Mistral Medium 3.5 model ID
- OpenRouter
mistralai/mistral-medium-3-5
Use the OpenRouter ID when calling it through OpenRouter; Mistral’s own API may name it differently. See the model ID reference for the providers we document.
Mistral
Where Mistral Medium 3.5 sits in Mistral’s line-up
Ranked by blended price (three parts input to one part output, $3 per 1M for Mistral Medium 3.5), it is the most expensive of Mistral’s 8 current models here. One step down, Mistral Large 4 costs $1.0325 blended (66% less). Unlike Mistral Medium 3.5, it doesn’t accept files and reads up to 1,048,576 tokens (262,144 here). See every Mistral model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Ministral 3 3B 2512 | $0.10 | $0.10 | 131,072 | 2025-12-02 |
| Ministral 3 8B 2512 | $0.15 | $0.15 | 262,144 | 2025-12-02 |
| Voxtral Small 24B 2507 | $0.10 | $0.30 | 32,768 | 2025-10-30 |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262,144 | 2025-12-02 |
| Mistral Small 4 | $0.15 | $0.60 | 262,144 | 2026-03-16 |
| Codestral 2508 | $0.30 | $0.90 | 128,000 | 2025-08-01 |
| Mistral Large 4 | $0.68 | $2.09 | 1,048,576 | 2026-10-06 |
| Mistral Medium 3.5 (this page) | $1.50 | $7.50 | 262,144 | 2026-04-30 |
Mistral’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of Mistral Medium 3.5
The previous model in this line is Mistral Medium 3.1, first listed on 2025-08-13. Compared with it, Mistral Medium 3.5’s input price is 275% higher and its output price is 275% higher, and the context window went from 131,072 to 262,144 tokens.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Medium 3.1 | $0.40 | $2 | 131,072 | 2025-08-13 |
| Mistral Medium 3 | $0.40 | $2 | 131,072 | 2025-05-07 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- Qwen3.6 35B A3BQwen90% cheaper
- GLM 4.6VZ.ai85% cheaper
- Muse Glimmer 30BMeta83% cheaper
- DeepSeek V4.1 FlashDeepSeek83% cheaper
- MiniMax M3MiniMax83% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Qwen3.8 Max (0902)Qwen$2 / $6
- Grok 4.7xAI$2 / $6
- Kimi K3Moonshot AI$0.80 / $10
- GPT-6.1 SolOpenAI$2 / $10
- Claude Sonnet 5.5Anthropic$2 / $10
Current models from other major providers, closest blended price.
FAQ
Mistral Medium 3.5 questions
How much does Mistral Medium 3.5 cost?
Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00525. Use the LLM cost calculator for your own workload.
What is Mistral Medium 3.5’s context window?
262,144 tokens, about 196,608 English words or 393 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Mistral Medium 3.5 support prompt caching and batch requests?
No cached-input price is published for it. A batch API is available at $0.75 input and $3.75 output per million tokens.
What are cheaper alternatives to Mistral Medium 3.5?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.6 35B A3B (90% cheaper), GLM 4.6V (85% cheaper), Muse Glimmer 30B (83% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Mistral Medium 3.5?
On OpenRouter it is mistralai/mistral-medium-3-5. Mistral’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
What did Mistral Medium 3.5 replace?
The previous Mistral model in the same line is Mistral Medium 3.1, first listed on 2025-08-13. Compared with it, Mistral Medium 3.5’s input price is 275% higher and its output price is 275% higher. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is Mistral Medium 3.5 open source?
No, Mistral Medium 3.5 is only available through Mistral’s API and partners; its weights aren’t published.