Mistral Medium 3.5
Intelligence
14.89
#267 of 520 models
Output speed
138.1 tok/s
Measured generation rate
Cost / index task
$0.437
Measured evaluation workload
End-to-end latency
20ms
First answer 17ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
29 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
- $1.50
- Output / 1M
- $7.50
- Cache read / 1M
- $0.150
- Cache write / 1M
- —
- Cache-hit discount
- 90%
Response & usage
- Output speed
- 138.1 tok/s
- First chunk
- 2ms
- First answer
- 17ms
- Output / task
- 26.1k
- Reasoning / task
- 14k
Evaluation workload
- Canonical input
- 1.47B
- Canonical output
- 100.69M
- Answer / task
- 12.1k
- Index time / task
- 2.9m
- Run cost
- $1,159.934
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 145.1 tok/s | 1ms | 14ms | 18ms |
| Long | 138.1 tok/s | 2ms | 17ms | 20ms |
| Hundred K | 145.3 tok/s | 35ms | 48ms | 52ms |
| Medium Parallel | 123.5 tok/s | 1ms | 17ms | 21ms |
04 / Access
License & availability
Recorded license
Modified MIT License
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Commercial License
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- mistralai/mistral-medium-3-5
- Tokenizer
- Mistral
- Instruct type
- —
- Captured endpoints
- 2
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| 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.