Context Window
65,536
Tokens
Model Cost Profile
Mistral: Mixtral 8x22B Instruct
Developer: mistralai
Pricing updated Mar 11, 2026
Input rank: #280Output rank: #264
Mistral: Mixtral 8x22B Instruct, developed by mistralai, offers a substantial context window of 65,536 tokens, making it suitable for complex tasks such as long-form content generation and detailed data analysis. Teams utilizing this API model can expect an input cost of $2.00 per million tokens and an output cost of $6.00 per million tokens, which can influence budgeting for projects requiring extensive interactions. This model is particularly advantageous for applications in natural language understanding and instruction-following scenarios, where maintaining context over large text spans is critical.
🔧 Tool Calling📋 Structured Output
Input Price / 1M
$2.00
Prompt tokens
Output Price / 1M
$6.00
Completion tokens
Intelligence (MMLU)
Benchmark Pending
Massive Multitask Language Understanding
Side-by-Side Pricing Table
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $2.00 |
| Output (Completion) | $6.00 |
Price History
Mistral: Mixtral 8x22B Instruct Pricing Trend
Input / 1M tokens0.0%Output / 1M tokens0.0%
Mar 7 — Mar 11
Current Input / 1M
$2.00
Current Output / 1M
$6.00
Cost Calculator
Estimate monthly spend for Mistral: Mixtral 8x22B Instruct based on your workload.
01.0B
0500M
Estimated Monthly Cost
$122
25M input + 12M output tokens
Cheaper Alternatives to Compare
Quick links for cost-down decisions before production rollout.
FAQ
Common pricing and benchmark questions for Mistral: Mixtral 8x22B Instruct.
How much does Mistral: Mixtral 8x22B Instruct cost per 1M input tokens?
Mistral: Mixtral 8x22B Instruct input pricing is $2.00 per 1M tokens based on the latest synced provider data.
How much does Mistral: Mixtral 8x22B Instruct cost per 1M output tokens?
Mistral: Mixtral 8x22B Instruct output pricing is $6.00 per 1M tokens based on the latest synced provider data.
What context window does Mistral: Mixtral 8x22B Instruct support?
Mistral: Mixtral 8x22B Instruct supports a context window of 65,536 tokens.
How can I compare Mistral: Mixtral 8x22B Instruct with cheaper alternatives?
Use the comparison links on this page to open direct model-vs-model pricing and benchmark pages, then evaluate monthly spend projections for your workload.