Mistral AIMinistral 3B (latest)
Not yet ranked: too few independent results so far. Released 16 Oct 2024.
- Blended price
- $0.040/M
- $0.040 in · $0.040 out
- Output speed
- 34 tok/s
- First answer
- 0.33 s
- Context
- 128k
- Reasoning22
- Maths30
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond | 25.3%#262 | Epoch AI Benchmarking Hub |
Maths
| Benchmark | default | Source |
|---|---|---|
| MATH Level 5 | 14.4%#79 | Epoch AI Benchmarking Hub |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 118.1#172 | Epoch AI Benchmarking Hub |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Mistral (ZDR) | 35 tok/s | 0.35 s | $0.100 | $0.100 | 131k | – |
| Mistral | 33 tok/s | 0.31 s | $0.100 | $0.100 | 131k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0000 | – | 9.2 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0005 | – | 18.0 s |
| Code edit | 6,000 / 1,500 | $0.0003 | – | 44.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.0026 | – | 2.0 min |
| Structured extraction | 2,000 / 200 | $0.0001 | – | 6.2 s |
See also
Data as of 9 Sept 2026. Compare with another model.