Mistral Large API Pricing
Mistral · Mid-tier · Mistral · released 2024-02. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.
- Input: $2.00 per 1M tokens
- Output: $6.00 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.20
- Context window: 128K
- Arena ELO: 1250 (as of 2026-08-13)
- Available on: Direct API, AWS Bedrock, Azure AI Foundry, OpenRouter (curated by hand — verify with the provider)
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads — only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0060 | $0.0044 | $438 |
| Knowledge Q&A | 2,000 / 800 | $0.0088 | $0.0063 | $628 |
| Meeting Summary | 10,000 / 1,200 | $0.027 | $0.025 | $2.5K |
| Marketing Content | 2,500 / 1,800 | $0.016 | $0.015 | $1.5K |
| Coding Task | 3,000 / 2,000 | $0.018 | $0.015 | $1.5K |
| Invoice Processing | 1,500 / 600 | $0.0066 | $0.0058 | $579 |
| Call Summary | 2,000 / 700 | $0.0082 | $0.0078 | $784 |
| Agent Workflow | 6,000 / 3,000 | $0.030 | $0.022 | $2.2K |
These are list prices — real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.