Mistral Medium 3.5
AI model by Mistral. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Mistral Medium 3.5 is positioned in the mid-tier at $7.50/M output tokens. The benchmark profile is balanced — strongest on Coding Index (46.9) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Mistral Medium 3.5 reports 132 tok/s output speed and 2280ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Mistral Medium 3.5 costs $2.25 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Mistral Medium 3.5Current | $1.50 | $7.50 | 132 tok/s |
| Qwen3 Coder 480B A35B Instruct | $1.50 | $7.50 | 66 tok/s |
| Qwen3.7 Max | $2.50 | $7.50 | 212 tok/s |
| Qwen3.6 Max Preview | $1.30 | $7.80 | 61 tok/s |
| o3 | $2.00 | $8.00 | 112 tok/s |
| GPT-4.1 | $2.00 | $8.00 | 142 tok/s |