Mistral · Model
Mistral Large 4 pricing, context window and specs
Mistral Large 4 costs $0.68 per million input tokens and $2.09 per million output tokens, and reads up to 1,048,576 tokens per request. By blended price it is number 16 of 20 from cheapest in Mistral's current line-up.
- Input / 1M
- $0.68
- Output / 1M
- $2.09
- Cached / 1M
- $0.07
- Context
- 1,048,576
- Max output
- 262,144
- Released
- 2026-10-06
Estimate your cost with Mistral Large 4Compare all Mistral modelsCount tokens for Mistral Large 4
Pricing
Mistral Large 4 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.68 | $2.09 |
| Cached input (read) | $0.07 | – |
Output costs 3.1× 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 Large 4 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.0014 | $42.54 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00439 | $66.81 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0119 | $72.15 |
| Document summariser | 8,000 / 600 | 300 | $0.00669 | $61.08 |
Change any number in the cost calculator.
Context
Context window
Mistral Large 4 accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 262,144 tokens.
Filling the whole window with one prompt costs about $0.71 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
- No
- 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 Large 4 sits in Mistral’s line-up
Ranked by blended price (three parts input to one part output, $1.0325 per 1M for Mistral Large 4), it is number 16 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 (this page) | $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 | $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
- Qwen3.5-9BQwen89% cheaper
- Seed 1.6 FlashByteDance Seed87% cheaper
- Claude Haiku 5.5Anthropic81% cheaper
- GPT-6 LunaOpenAI81% cheaper
- DeepSeek V4 Flash Vision ExpDeepSeek69% 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
- Qwen3.6 27BQwen$0.45 / $2.70
- Seed 2.1 TurboByteDance Seed$0.50 / $2.50
- GLM 4.7Z.ai$0.60 / $2.20
- Kimi K2 ThinkingMoonshot AI$0.60 / $2.50
- Gemini 3 Flash PreviewGoogle$0.50 / $3
Current models from other major providers, closest blended price.
FAQ
Mistral Large 4 questions
How much does Mistral Large 4 cost?
Mistral Large 4 costs $0.68 per million input tokens and $2.09 per million output tokens, with cached input at $0.07. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00186. Use the LLM cost calculator for your own workload.
What is Mistral Large 4's context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. A single reply can be up to 262,144 tokens.
Does Mistral Large 4 support prompt caching and batch requests?
Yes, cached input is billed at $0.07 per million tokens (10% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Mistral Large 4?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.5-9B (89% cheaper), Seed 1.6 Flash (87% cheaper), Claude Haiku 5.5 (81% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is Mistral Large 4 open source?
No, Mistral Large 4 is only available through Mistral's API and partners; its weights aren't published.