mistralai Open weights

Mixtral 8x22B Instruct pricing & benchmarks

Released Apr 17, 2024 · served by 1 provider

Input / 1M tokens$2.00
Output / 1M tokens$6.00
Context window66K
Cached input$0.200
1M in + 300K out$3.80

What Mixtral 8x22B Instruct is

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,...

Providers and prices for Mixtral 8x22B Instruct

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Mistralcheapest $2.00 $6.00 66K 100.0%

FAQ

How much does the Mixtral 8x22B Instruct API cost?

$2.00 per 1M input tokens and $6.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $3.80.

Is Mixtral 8x22B Instruct free?

No. It is a paid model starting at $2.00 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Mixtral 8x22B Instruct?

Mistral at $2.00 input / $6.00 output per 1M tokens.

Can I self-host Mixtral 8x22B Instruct?

Yes — weights are published as mistralai/Mixtral-8x22B-Instruct-v0.1 on Hugging Face, so you can run it on your own hardware.