Mistral Small 3.1 24 B Instruct pricing
Source: openrouter · updated 2026-11-18
Short answer: Mistral Small 3.1 24 B Instruct costs $0.351 per million input tokens and $0.555 per million output tokens. That is a 3:1 blended rate of $0.402 per million tokens, ranking it #395 of 833 tracked models by input price.
Input / 1M
$0.351
Output / 1M
$0.555
Output ÷ input
1.58×
Context window
128,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.351 |
| Output, per 1M tokens | $0.555 |
| Output ÷ input multiple | 1.58× |
| 3:1 blended, per 1M tokens | $0.402 |
| Context window | 128,000 tokens |
| Vendor | mistralai |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.351 | $0.139 | $0.490 |
| 10M in / 2.5M out | $3.51 | $1.39 | $4.90 |
| 100M in / 25M out | $35.10 | $13.88 | $48.98 |
Other mistralai models
| Model | Input | Output |
|---|---|---|
| Mistral Nemo | $0.029 | $0.030 |
| Mistral Small 24 B Instruct 2501 | $0.050 | $0.080 |
| Mistral Small 3.2 24 B Instruct | $0.075 | $0.200 |
| Ministral 3 B2512 | $0.100 | $0.100 |
| Voxtral Small 24 B2507 | $0.100 | $0.300 |
Compare against
- Mistral Small 3.1 24 B Instruct vs Gemma Sea Lion V4 27 B It
- Mistral Small 3.1 24 B Instruct vs Qwen 3 235 B A22 B Thinking 2507 Fp 8
Cheaper alternatives
Next cheaper option: Qwen 3 235 B A22 B Fp 8 at $0.170 per 1M input tokens. Next step up: GLM Latest at $0.070 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.