Mistral Small 3 pricing & specs
Mistral · released 2025-01-30 · ● verified 2026-10-15
input / 1M$0.05via DeepInfra
output / 1M$0.08via DeepInfra
context32.8K
max output16.4K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Mistral Small 3 |
|---|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | 131K | −65.2% |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | 16.4K | −52.2% |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | 32.8K | −30.4% |
| Gemma 3 4B IT | $0.04 | $0.08 | 131.1K | −13% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −13% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| DeepInfra | $0.05 | $0.08 |
// faq
How much does Mistral Small 3 cost?
Mistral Small 3 costs $0.05 per million input tokens and $0.08 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $3.30.
What is the context window of Mistral Small 3?
32.8K tokens, with up to 16.4K output tokens per request.
What are cheaper alternatives to Mistral Small 3?
Llama 3.2 1B Instruct ($0.02 in / $0.02 out), Llama-3.1-8B-Instruct ($0.02 in / $0.05 out), Voxtral Mini 3B 2507 ($0.04 in / $0.04 out) offer the same input types and capabilities for less.
Is Mistral Small 3 open weights?
Yes. It is available from 1 tracked hosts; the cheapest is DeepInfra at $0.05 input and $0.08 output per million tokens.
// spec sheet
- input / 1M
- $0.05
- output / 1M
- $0.08
- blended (3:1)
- $0.0575
- context
- 32.8K
- max output
- 16.4K
- input types
- text
- reasoning
- no
- tool calling
- no
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- 2023-10-31
- price source
- DeepInfra
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | $1.50 |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | $2.40 |
| Mistral Small 3 | $0.05 | $0.08 | $3.30 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.