Mistral Large 4 API Pricing
The provider marks this model as beta or experimental. Its price and availability may change.
Mistral · released Oct 6, 2026 · 1.05M context · API model ID mistral-large-4
Mistral Large 4 by Mistral API pricing: $0.68 per 1M input tokens and $2.09 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $0.68 |
| Output | $2.09 |
| Cache read | $0.07 |
| Cache write | Not published |
Mistral's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$517.50
per month
- per day
- $17.25
- per request
- $0.00172
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $517.50/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $972.75/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $413.40/mo |
Context and capabilities
- Context
- 1,048,576 tokens
- Max output
- 262,144 tokens
- Input
- text, image
- Output
- text
- Knowledge cutoff
- Not published
- Open weights
- No
- Tool calling
- Yes
- Reasoning
- Yes
- Structured outputs
- Yes
Capabilities and limits as listed by models.dev.
Similarly priced models
- Seed 2.0 Pro · $0.50 in / $3.00 out
- Grok Build 0.1 · $1.00 in / $2.00 out
- Gemini 3.5 Flash Lite · $0.30 in / $2.50 out
- Gemini 3.8 Flash · $0.75 in / $3.75 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does Mistral Large 4 cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Mistral Large 4 costs about $517.50 per month at Mistral's list prices ($0.68 per 1M input tokens, $2.09 per 1M output tokens).
- Does Mistral Large 4 support prompt caching?
- Yes. Cached input costs $0.07 per 1M tokens, compared with $0.68 for regular input.
- How long is Mistral Large 4's context window?
- Mistral Large 4 accepts up to 1,048,576 tokens (1.05M) of context and returns up to 262,144 tokens per response.