Mistral Large 4 vs Mistral Medium 3.5
Side by side: price, limits, capabilities and real cost examples. Catalog data · checked Nov 16, 2026
Short answer
- Mistral Large 4 is about 2.9× cheaper than Mistral Medium 3.5 for a typical mix of three parts input and one part output.
- Mistral Large 4 reads 4× more text per request (1.05M vs 262.1K tokens).
- A quality verdict needs a hands-on test. Neither model has completed our Hero suite yet, so this page compares facts, not output quality.
| Mistral Large 4Mistral AI | Mistral Medium 3.5Mistral AI | |
|---|---|---|
| Input price / 1M tokens | $0.7 | $1.5 |
| Output price / 1M tokens | $2.1 | $7.5 |
| Context window | 1.05M | 262.1K |
| Max output per answer | 262.1K | 262.1K |
| Released | Oct 2026 | Apr 2026 |
| Tool calling | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Image input | Yes | Yes |
| File input | Yes | Yes |
| Prompt caching | Yes | Yes |
| What it costs in practice | ||
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $1.09 | $3.08 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.109 | $0.24 |
| 10,000 product descriptions300 input and 200 output tokens per text | $6.3 | $19.5 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $2.42 | $5.63 |
Green marks the better value in that row. Prices are first-party list prices in USD. Method.
