Mistral: Mistral Medium 3
mistralai/mistral-medium-3
Mistral Medium 3 is Mistral's budget option at $0.4/$2 per million input/output tokens, with a 131K-token context. It sits toward the back of the board on capability, at #173 of 235 on the TryAii Score — its best showing is #33 on AA-Omniscience-Hallucination-Rate.
Prompt $/1M
$0.400
Completion $/1M
$2.000
Context
131,072 tok
Best provider
18 tok/s · Mistral
Specs
- Model id
- mistralai/mistral-medium-3
- Display name
- Mistral: Mistral Medium 3
- Modality
- text+image+file->text
- Tokenizer
- Mistral
- Instruct type
- —
- Context length
- 131,072
- Max completion
- 104,857
- Prompt $/1M
- $0.400
- Completion $/1M
- $2.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Mistralfastest | 18 |
| mistralaifastest | — |
| Artificial Analysis | 0 |