Mistral3 providers available

Mixtral 8×7B

Mixtral 8×7B — Mistral's open MoE model widely available on 15+ providers; efficient sparse inference with strong multilingual performance.

🔧 Tool Use🆓 Open Source

Best price

$0.540

per 1M input tokens

Best benchmark

—

top score across benchmarks

Providers

APIs serving this model

📄Context

33K

max token window

Compare providers

Provider / Variant	Input $/1M	Output $/1M	Latency	Context
BEST PRICE mistralai Mistral: Mixtral 8x7B Instruct	$0.540	$0.540	—	33k	Details Use
mistralai Mixtral-8x7B Instruct v0.1	$0.600	$0.600	226ms	33k

Compare with another model

See how Mixtral 8×7B stacks up side-by-side.

Looking for alternatives?

Find cheaper or faster models in the same class.

Quick comparisons