Mistral · Model
Mistral Small 4 pricing, context window and specs
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens, and reads up to 262,144 tokens per request. By blended price it is number 8 of 20 from cheapest in Mistral's current line-up.
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Cached / 1M
- $0.015
- Context
- 262,144
- Max output
- Not published
- Released
- 2026-03-16
Estimate your cost with Mistral Small 4Compare all Mistral modelsCount tokens for Mistral Small 4
Pricing
Mistral Small 4 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.15 | $0.60 |
| Cached input (read) | $0.015 | – |
| Batch API | $0.075 | $0.30 |
Output costs 4.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price.
Examples
What Mistral Small 4 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000364 | $11.06 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00104 | $15.79 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00288 | $17.52 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.00078 | $7.12 |
Change any number in the cost calculator.
Context
Context window
Mistral Small 4 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 $0.0393 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
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text, image
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
Mistral
Where Mistral Small 4 sits in Mistral’s line-up
Ranked by blended price (three parts input to one part output, $0.2625 per 1M for Mistral Small 4), it is number 8 of 20 from cheapest of Mistral’s 20 priced models. See every Mistral model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Large 4 | $0.68 | $2.09 | 1,048,576 | 2026-10-06 |
| Mistral Medium 3.5 | $1.50 | $7.50 | 262,144 | 2026-04-30 |
| Mistral Small 4 (this page) | $0.15 | $0.60 | 262,144 | 2026-03-16 |
| Devstral 2 2512 | $0.40 | $2 | 262,144 | 2025-12-09 |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262,144 | 2025-12-02 |
| 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 |
| Mistral Large 3 2512 | $0.50 | $1.50 | 262,144 | 2025-12-01 |
Save
Cheaper alternatives
- Qwen3.7 FlashQwen79% cheaper
- Gemma 4 26B A4BGoogle54% cheaper
- Muse Spark 1.2 ContributorMeta52% cheaper
- Seed 1.6 FlashByteDance Seed50% cheaper
- Claude Haiku 5.5Anthropic24% 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 Coder NextQwen$0.12 / $0.80
- GLM 5.3 FlashZ.ai$0.15 / $0.50
- DeepSeek V3.2DeepSeek$0.259 / $0.42
- Claude Haiku 5.5Anthropic$0.10 / $0.50
- GPT-6 LunaOpenAI$0.10 / $0.50
Current models from other major providers, closest blended price.
FAQ
Mistral Small 4 questions
How much does Mistral Small 4 cost?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens, with cached input at $0.015. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.000465. Use the LLM cost calculator for your own workload.
What is Mistral Small 4'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 Small 4 support prompt caching and batch requests?
Yes, cached input is billed at $0.015 per million tokens (10% of the normal input price). A batch API is available at $0.075 input and $0.30 output per million tokens.
What are cheaper alternatives to Mistral Small 4?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.7 Flash (79% cheaper), Gemma 4 26B A4B (54% cheaper), Muse Spark 1.2 Contributor (52% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is Mistral Small 4 open source?
Yes, Mistral Small 4 has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.