Pixtral 12B pricing & specs
Mistral · released 2024-09-01 · ● verified 2026-10-11 · deprecated
This model is deprecated. Cheapest compatible replacement: Gemma 4 E2B IT.
input / 1M$0.15
output / 1M$0.15
context128K
max output128K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Pixtral 12B |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −66.7% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −63.3% |
| Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | −58.3% |
| Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | −33.3% |
| Ministral 3 3B | $0.10 | $0.10 | 131.1K | −33.3% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Scaleway | $0.20 | $0.20 |
// faq
How much does Pixtral 12B cost?
Pixtral 12B costs $0.15 per million input tokens and $0.15 per million output tokens. At 50M input and 10M output tokens per month that is about $9.00.
What is the context window of Pixtral 12B?
128K tokens, with up to 128K output tokens per request.
What are cheaper alternatives to Pixtral 12B?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Gemma 3 12B IT ($0.05 in / $0.10 out) offer the same input types and capabilities for less.
Is Pixtral 12B open weights?
Yes. It is available from 1 tracked hosts; the cheapest is Scaleway at $0.20 input and $0.20 output per million tokens.
// spec sheet
- input / 1M
- $0.15
- output / 1M
- $0.15
- blended (3:1)
- $0.15
- context
- 128K
- max output
- 128K
- input types
- text · image
- reasoning
- no
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- 2024-09
- price source
- Mistral
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Gemma 3 12B IT | $0.05 | $0.10 | $3.50 |
| Pixtral 12B | $0.15 | $0.15 | $9.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.