Mistral: Mixtral 8x7B Instruct
mistralai/mixtral-8x7b-instruct
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion...
Prompt $/1M
$0.540
Completion $/1M
$0.540
Context
32,768 tok
Best provider
47 tok/s · Together
Specs
- Model id
- mistralai/mixtral-8x7b-instruct
- Display name
- Mistral: Mixtral 8x7B Instruct
- Modality
- text->text
- Tokenizer
- Mistral
- Instruct type
- mistral
- Context length
- 32,768
- Max completion
- 16,384
- Prompt $/1M
- $0.540
- Completion $/1M
- $0.540
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionno
- 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 |
|---|---|
| Together | 47 |
| DeepInfrafastest | 36 |
| mistralaifastest | — |