Mistral Small 4
Intelligence
11.45
#326 of 520 models
Output speed
173.4 tok/s
Measured generation rate
Cost / index task
$0.045
Measured evaluation workload
End-to-end latency
15ms
First answer 12ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
25 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $0.150
- Output / 1M
- $0.600
- Cache read / 1M
- —
- Cache write / 1M
- —
- Cache-hit discount
- —
Response & usage
- Output speed
- 173.4 tok/s
- First chunk
- 1ms
- First answer
- 12ms
- Output / task
- 14.4k
- Reasoning / task
- 9.4k
Evaluation workload
- Canonical input
- 308.95M
- Canonical output
- 53.92M
- Answer / task
- 5k
- Index time / task
- 1.5m
- Run cost
- $78.696
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 169.6 tok/s | 1ms | 12ms | 15ms |
| Long | 173.4 tok/s | 1ms | 12ms | 15ms |
| Hundred K | 128.4 tok/s | 5ms | 21ms | 25ms |
| Medium Parallel | 162.4 tok/s | 1ms | 13ms | 16ms |
04 / Access
License & availability
Recorded license
Apache 2.0
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Permissive
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- mistralai/mistral-small-2603
- Tokenizer
- Mistral
- Instruct type
- —
- Captured endpoints
- 3
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Mistral | unknown | 262.1k | — |
| Mistral | unknown | 262.1k | — |
| Mistral | unknown | 262.1k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.