Mistral Medium 3.5 pricing
Mistral AI · API id mistral-medium-latest · verified 2026-10-18
| Input | $1.50 |
| Cached input (cache hit) | $0.15 |
| Cache write | — |
| Output | $7.50 |
| Batch discount | 50% |
| Context window | 256,000 tokens |
| Max output | — |
USD per 1M tokens unless noted. Official source
Estimate your workload on Mistral Medium 3.5 →
What Mistral Medium 3.5 costs for real workloads
| Workload | Mistral Medium 3.5 | Grok 4.3 | Gemini 3.8 Flash | Gemini 3.6 Flash | Claude Sonnet 5.5 |
|---|---|---|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $46.50 | $24.50 | $23.25 | $23.25 | $61.00 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.72 | $0.64 | $0.36 | $0.36 | $0.83 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $525 | $640 | $263 | $263 | $700 |
Compared with the cheapest other mid models. Change the numbers in the calculator.
Billing notes
Aliases mistral-medium-3-5, mistral-medium-3. Pricier than Large 4 sale price. Batch 50% off per mistral.ai/pricing. Max output not published.
Where Mistral Medium 3.5 ranks by use case
Position by cost among all models that fit each workload (1 = cheapest).
- Cheapest LLM for coding agents: #20 of 36 (Per run (cached): $0.72)
- Cheapest LLM for RAG chatbots: #20 of 36 (Per 1,000 answers: $9.97)
- Cheapest LLM for batch classification and extraction: #16 of 36 (Classify 1M docs: $525)
- Cheapest LLM for high-volume customer support: #20 of 36 (Per 1,000 replies: $3.98)
Counting tokens for a prompt? The token counter estimates Mistral Medium 3.5 tokens (xAI, DeepSeek, Mistral tokenizer, estimated) and input cost.
Head-to-head comparisons
Other Mistral AI models
- Mistral Large 4: $0.68 / $2.09
- Codestral: $0.30 / $0.90
- Mistral Small 4: $0.15 / $0.60
- Ministral 3 8B: $0.15 / $0.15
FAQ
How much does Mistral Medium 3.5 cost per 1M tokens?
Mistral Medium 3.5 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens at standard rates (verified 2026-10-18).
Does Mistral Medium 3.5 support prompt caching?
Yes. Cached input is billed at $0.15 per 1M tokens.
Is there a batch discount for Mistral Medium 3.5?
Yes. The batch API is 50% cheaper than standard requests.
What is the context window of Mistral Medium 3.5?
256,000 tokens.