← All models
Balanced — strong quality at a mid priceOpen Weights
Mixtral 8x22B Instruct Pricing
Mistral AI · mistralai-mixtral-8x22b-instruct
Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Context window
65,536 tokens
≈ 87 pages of text
Max output
—
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0048
1,000 requests / month$4.80/mo10,000 requests / month$48.00/mo100,000 requests / month$480.00/moEstimate your own workloadOpens the calculator with Mixtral 8x22B Instruct preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Performs well on instruction following, code generation, and multilingual tasks. 64k context supports long-document processing at moderate cost.
The business tradeoff
Output tokens priced three times higher than input. Open weights require self-hosting with variable latency and infrastructure overhead.
Cheaper from Mistral AI
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.