Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct
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,...
Source: OpenRouter (live)
- Input
- $2.00
- USD per 1M tokens
- Output
- $6.00
- USD per 1M tokens
- Blended
- $3.00
- 75% in / 25% out
- Context
- 66K
- tokens
- Max output
- 52K
- tokens
- Modality
- text+file->text
Prices as listed on OpenRouter, refreshed every five minutes. Provider-direct prices may differ. Convert to your currency on the AI Tracker.
Capabilities
Declared on the listing
- Tool / function calling Declared
- Reasoning controls Not declared
- Structured output Declared
- InputText, File
- OutputText
Capabilities are read from the provider listing. “Not declared” means the listing does not advertise the feature, not that it is absent.
Why it costs this
Pricing context
- 3.8× median
- Market median blended price is $0.800/M across 417 priced models.
Alternatives
More from Mistral
$1.50
/M blended
Mistral
$3.00
/M blended
$0.131
/M blended
Mistral
$0.262
/M blended
Mistral
$0.800
/M blended
$0.200
/M blended
Alternatives
Similar price, other providers
Anthropic: Claude Sonnet 4.6 (batch)
Anthropic
$3.00
/M blended
Anthropic: Claude Sonnet 4.5 (batch)
Anthropic
$3.00
/M blended
Sakana
$3.00
/M blended
Qwen (Alibaba)
$3.00
/M blended
Qwen (Alibaba)
$3.00
/M blended
Qwen: Qwen3.8 2.4T A95B (batch)
Qwen (Alibaba)
$3.00
/M blended
Within ±50% of $3.00/M blended.
European lab with open and commercial models. All Mistral models · Official site
Newsletter
Stay Ahead of AI
Get the most important developments in artificial intelligence delivered directly to your inbox.
No hype. No spam.
Just trusted insights, major model releases, pricing updates, benchmark changes, product reviews, and practical guidance from across the AI ecosystem.
- Weekly AI Briefing
- Major Model Releases
- Pricing & Benchmark Updates
- Unsubscribe Anytime
The AI HQ Briefing
One email a week. Read in five minutes.