Mistral: Mixtral 8x22B Instruct
Provider: mistralai · mistralai/mixtral-8x22b-instruct
How Mistral: Mixtral 8x22B Instruct pricing compares
At $6 / 1M output tokens, Mistral: Mixtral 8x22B Instruct is the 18th-cheapest of 20 mistralai models we track. It's cheaper than 24% of the 392 paid models on computetrail (297th-cheapest overall). Output costs 3.0× its input price ($2 / 1M in). For a typical 3:1 input-to-output workload that works out to about $3.00 / 1M blended. Reading cached input costs 90% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 65,536 tokens context window ranks 361st-largest of 392 models with a published limit.
Output price history
Across 60 daily snapshots since 2026-06-29, the output price has held steady at $6 / 1M — no change so far.
Similar-priced models
| Model | Provider | Output $/1M | Context |
|---|---|---|---|
| SpaceXAI: Grok 4.6 | x-ai | $6 | 500,000 |
| SpaceXAI: Grok 4.5 | x-ai | $6 | 500,000 |
| Mistral Large | mistralai | $6 | 128,000 |
| Google: Gemini 2.5 Pro (batch) | $5 | 1,048,576 | |
| Google: Gemini 3.5 Flash (batch) | $4.5 | 1,048,576 | |
| Mistral: Mistral Medium 3.5 | mistralai | $7.5 | 262,144 |
Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.