Mistral Medium 3.5 API Pricing
Mistral · Mid-tier · Mistral · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.
- Input: $1.50 per 1M tokens
- Output: $7.50 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: not published
- Context window: 262K
- 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 | $0.0060 | $600 |
| Knowledge Q&A | 2,000 / 800 | $0.0090 | $0.0090 | $900 |
| Meeting Summary | 10,000 / 1,200 | $0.024 | $0.024 | $2.4K |
| Marketing Content | 2,500 / 1,800 | $0.017 | $0.017 | $1.7K |
| Coding Task | 3,000 / 2,000 | $0.019 | $0.019 | $1.9K |
| Invoice Processing | 1,500 / 600 | $0.0067 | $0.0067 | $675 |
| Call Summary | 2,000 / 700 | $0.0083 | $0.0083 | $825 |
| Agent Workflow | 6,000 / 3,000 | $0.032 | $0.032 | $3.1K |
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.