TokenRate

Mixtral 8x22B Instruct Pricing

Balanced

Mistral · 66K tokens context

Mixtral 8x22B Instruct from Mistral costs $2.00 per 1 million input tokens and $6.00 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 65,536-token context window (approximately 49,152 words) with a 16K-token maximum output. A typical 1,000-token request costs $0.0020 in input charges; a 10,000-token request costs $0.0200.

Mixtral 8x22B Instruct pricing and capability summary
Input price$2.00 / 1M tokens
Output price$6.00 / 1M tokens
Output / input ratio3.0×
Context window65,536 tokens (~49,152 words)
Maximum output16,000 tokens
Cost per 1K tokens (input)$0.0020
TierBalanced
Last verified

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.

Live pricing from OpenRouter

Input Price

$2.00

per 1 million tokens

Output Price

$6.00

per 1 million tokens

Context Window

66K tokens

max 16K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.00267$0.0024
10-page document (2,500 words)3,333$0.00667$0.006
1,000 lines of code5,000$0.01$0.009
100K token document100,000$0.20$0.18

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Strong general-purpose performance
  • Strong general-purpose performance
  • Strong general-purpose performance

Limitations

  • Quality and availability can vary by hosting provider
  • Quality and availability can vary by hosting provider

Best Use Cases

Customer-facing AI apps
Code generation and review
Content creation at scale
Conversational interfaces

Calculate Mixtral 8x22B Instruct Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Mixtral 8x22B Instruct costs — and compare across all models.

Open Calculator →

Mixtral 8x22B Instruct — FAQ

Related Models

Related Guides