Mixtral 8x22B
Pricing & Specs

Mistral · $2 input / $6 output per 1M tokens · 65.536K context window

$2
per 1M input tokens
$6
per 1M output tokens
65.536K
context window (tokens)

The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Mixtral 8x22B costs about $0.0050 — roughly $5.00 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.

Mixtral 8x22B API Pricing

TokensPrice
Input$2 / 1M tokens
Output$6 / 1M tokens

50% discount available for batch API requests. Batch API pricing is available for this model at 50%. No cache pricing is published.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0050
1K 1,000 runs of that task: $5.00
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Mixtral 8x22B Specs

SpecValue
Context window65.536K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~147ms median response
Reasoning modelNo
Tool / function callingNo
JSON modeYes
StreamingYes
Prompt cachingNo
Batch APIYes

Capabilities

text generation streaming structured outputs

FAQ

How much does Mixtral 8x22B cost?

Mixtral 8x22B costs $2 per 1M input tokens and $6 per 1M output tokens.

What is Mixtral 8x22B's context window?

Mixtral 8x22B has a 65.536K-token context window.

Can I test Mixtral 8x22B on my own task?

Yes. OpenMark lets you benchmark Mixtral 8x22B against 100+ models on your own task with real API calls — no API keys needed, free tier available.

Is Mixtral 8x22B the right model for YOUR task?

Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.

Benchmark Mixtral 8x22B — Free →