The Orchestrator › Models › Mistral AI
Mistral AI: Mistral: Mixtral 8x22B Instruct
Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/mixtral-8x22b-instruct |
| Context window | 66K tokens (65,536) |
| Modalities | text + file → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter |
| Released | 2024-04-17 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/mixtral-8x22b-instruct | $2.00 | $6.00 | 66K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.00 | $6.00 | 66K |
Capabilities
File inputAgentic tool useStructured outputs
Supported parameters
frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p