← Model list
Mistral Medium (latest)
mistral·mistral/mistral-medium-latest·GA·Open weights·mistral-medium series
Balanced Mistral model for enterprise assistants, multilingual work, and tools
At a glance
Official price$1.50 / $7.50 per 1M
Cache read — · Mistral
Lowest paid$0.396 / $1.98
Requesty Gateway · 3.8× spread
Context262,144
⚠ Providers report 131,072–262,144; the table below is authoritative
Output limit262,144
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff—
Released / updated2026-04-29 / 2026-04-29
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 5 providers5 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Requesty | Gateway | $0.396 | $1.98 | $0.396 | — | 131,072 ⚠ | 131,072 | |
| Merge Gateway | Gateway | $0.40 | $2.00 | — | — | 262,144 | 262,144 | |
| MistralOfficial | First-party | $1.50 | $7.50 | — | — | 262,144 | 262,144 | |
| Vercel AI Gateway mistral/mistral-medium-3.5 | Cloud | $1.50 | $7.50 | — | — | 256,000 ⚠ | 256,000 | |
| Eden AI | Gateway | $1.50 | $7.50 | — | — | 262,144 | 262,144 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Requesty$178.20
2Merge Gateway$180.00
3Mistral · Official$675.00
4Vercel AI Gateway$675.00
5Eden AI$675.00
Switch to Requesty to save $496.80/mo (74%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark1 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 77.6 | resolved | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = high
1 / 5 providers expose no reasoning control (reasoning_options: []).
Related models
Mistral Medium 3.5 Thinkingsame series$1.50 / $7.50mistral-medium-3-5@eusame series$1.49 / $7.42Mistral: Mistral Medium 3.5same series$1.50 / $7.50Kimi K2.6cheaper alternative$0.95 / $4.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28Kimi K2.7 Codecheaper alternative$0.95 / $4.00
Price historyone sample accumulated per data sync
Input listOutput listMin blended