← Model list
Mistral Medium 3
mistral·mistral/mistral-medium-2505·GA·Closed·mistral-medium series
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
At a glance
Official price$0.40 / $2.00 per 1M
Cache read — · Mistral
Lowest paid$0.40 / $2.00
NanoGPT Gateway · 1× spread
2 more $0 channels
Context131,072
⚠ Providers report 128,000–131,072; the table below is authoritative
Output limit131,072
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-05
Released / updated2025-05-07 / 2025-05-07
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence12.5
Value16
Coding—
Agentic—
Output speed57 tok/s
TTFT1.47 s
Value formulaIQ 12.5 ÷ min blended $0.800 = 16
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 9 providers7 with public prices · 2 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia mistralai/mistral-medium-3-instruct | First-party | Free | — | — | 131,072 | 32,768 | ||
| EmpirioLabs AI mistral-medium-3 | Gateway | Free | — | — | 130,000 ⚠ | 40,000 | ||
| NanoGPT mistralai/mistral-medium-3 | Gateway | $0.40 | $2.00 | $0.20 | — | 131,072 | 32,768 | |
| OpenRouter mistralai/mistral-medium-3 | Gateway | $0.40 | $2.00 | $0.04 | — | 131,072 | 131,072 | |
| Merge Gateway | Gateway | $0.40 | $2.00 | $0.04 | — | 128,000 ⚠ | 128,000 | |
| Azure Cognitive Services | First-party | $0.40 | $2.00 | — | — | 128,000 ⚠ | 128,000 | |
| Azure | First-party | $0.40 | $2.00 | — | — | 128,000 ⚠ | 128,000 | |
| MistralOfficial | First-party | $0.40 | $2.00 | — | — | 131,072 | 131,072 | |
| Eden AI | Gateway | $0.40 | $2.00 | — | — | 131,072 | 131,072 |
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
1OpenRouter$136.80
2Merge Gateway$136.80
3NanoGPT$156.00
4Azure Cognitive Services$180.00
5Azure$180.00
6Mistral · Official$180.00
2 more channels offer $0 (Nvidia, EmpirioLabs AI); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to OpenRouter to save $43.20/mo (24%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark3 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 13.6 | index | Source ↗ |
| SciCode | — | 33.1 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 3.8 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
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 / $7.50Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Qwen3-Coder 30B-A3B Instructcheaper alternative$0.216 / $0.861Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45Qwen3 Coder Flashcheaper alternative$0.144 / $0.574
Price historyone sample accumulated per data sync
Input listOutput listMin blended