Mixtral 8x22B Instruct
mistral/mixtral-8x22b-0-1-0-3
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Model information
Released
2024-04-17
Context window
66K
Weights
Open
Modalities
Input
DocumentText
Output
Text
Identity
- Version
- mixtral-8x22b-instruct
- Knowledge cutoff
- 2024-01-31
Resources
Capabilities
Open weightStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | mistralai/mixtral-8x22b-instruct | openai_chat | 66K | - | AttachmentsTool callStructuredTemperature | Hugging Face: mistralai/Mixtral-8x22B-Instruct-v0.1 | input $2/M · output $6/M cache read $0.2/M | Yes | ||
| Nvidia | mistralai/mixtral-8x22b-instruct | openai_chat | 66K | - | Tool callTemperature | - | input $0/M · output $0/M | Yes | ||
| Kilo Gateway | mistralai/mixtral-8x22b-instruct | openai_chat | 66K | - | AttachmentsTool callStructuredTemperature | - | input $2/M · output $6/M cache read $0.2/M | Yes | ||
| Mistral | mixtral-8x22b-instruct | custom | 66K | - | - | - | - | Yes |