Mixtral 8x22B pricing & specs
Mistral · released 2024-04-17 · ● verified 2026-10-11 · deprecated
This model is deprecated. Cheapest compatible replacement: Llama 3.2 1B Instruct.
input / 1M$2.00
output / 1M$6.00
context64K
max output64K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Mixtral 8x22B |
|---|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | 131K | −99.3% |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | 32.8K | −98.7% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −98.3% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −98.2% |
| Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | −97.9% |
// faq
How much does Mixtral 8x22B cost?
Mixtral 8x22B costs $2.00 per million input tokens and $6.00 per million output tokens. At 50M input and 10M output tokens per month that is about $160.
What is the context window of Mixtral 8x22B?
64K tokens, with up to 64K output tokens per request.
What are cheaper alternatives to Mixtral 8x22B?
Llama 3.2 1B Instruct ($0.02 in / $0.02 out), Voxtral Mini 3B 2507 ($0.04 in / $0.04 out), Gemma 4 E2B IT ($0.04 in / $0.08 out) offer the same input types and capabilities for less.
Is Mixtral 8x22B open weights?
Yes.
// spec sheet
- input / 1M
- $2.00
- output / 1M
- $6.00
- blended (3:1)
- $3.00
- context
- 64K
- max output
- 64K
- input types
- text
- reasoning
- no
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- 2024-04
- price source
- Mistral
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | $2.40 |
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Mixtral 8x22B | $2.00 | $6.00 | $160 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.