Mixtral 8x22B Instruct
$2.00 per 1M input tokens and $6.00 per 1M output tokens · 66K context · tools, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Mixtral 8x22B Instruct costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $835 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $209 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $378 |
| Content generation 30 long articles a day | $18.90 |
| Classification / extraction 100,000 short items a day | $2,070 |
Price history
We started tracking Mixtral 8x22B Instruct on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Mixtral 8x22B Instruct: 3 providers
Mistral is the cheapest at $2.00 input / $6.00 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
Cheaper alternatives to Mixtral 8x22B Instruct
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Muse Spark 1.3 Meta | $1.25 | $4.25 | 1.05M | visiontoolsreasoningJSON |
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| GLM 5.3 Z.ai | $0.079 | $1.40 | 1.05M | toolsreasoningJSONopen weights |
| Step 5 Preview Stepfun | $1.00 | $2.70 | 1.05M | visiontoolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
How to pay less for Mixtral 8x22B Instruct
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $1,224 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Muse Spark 1.3 (similar capabilities) | $569 | $655 (53%) |
| Use prompt caching (60% of input cached) | $835 | $389 (32%) |
Other workloads: cut-your-bill tool for Mixtral 8x22B Instruct.
Specifications
| Model ID | mistralai/mixtral-8x22b-instruct |
| Input | text, file |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | No |
| Open weights | Yes — mistralai/Mixtral-8x22B-Instruct-v0.1 |
| Knowledge cutoff | 2024-01-31 |
| Released | Apr 17, 2024 |
FAQ
- How much does Mixtral 8x22B Instruct cost?
- $2.00 per million input tokens and $6.00 per million output tokens; cached input costs $0.20 per million. Prices as of Oct 21, 2026.
- What is the context window of Mixtral 8x22B Instruct?
- 66K tokens, with up to 52K output tokens per response.
- Does Mixtral 8x22B Instruct support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: no.
- What are cheaper alternatives to Mixtral 8x22B Instruct?
- Models with the same key capabilities for at least 20% less include Muse Spark 1.3 ($1.25 / $4.25), MiMo-V2.6-Pro ($0.435 / $0.87), GLM 5.3 ($0.079 / $1.40).
More from Mistral AI: all Mistral AI models · how we collect prices