Mistral Small 3.2 24 B Instruct 2506 pricing
Source: litellm · updated 2026-10-27
Short answer: Mistral Small 3.2 24 B Instruct 2506 costs $0.090 per million input tokens and $0.280 per million output tokens. That is a 3:1 blended rate of $0.138 per million tokens, ranking it #115 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.090 |
| Output, per 1M tokens | $0.280 |
| Output รท input multiple | 3.11× |
| 3:1 blended, per 1M tokens | $0.138 |
| Context window | 128,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.090 | $0.070 | $0.160 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $0.900 | $0.700 | $1.60 | ||||
| 100M in / 25M out | $9.00 | $7.00 | $16.00 |
Other ovhcloud models
| Model | Input | Output |
|---|---|---|
| Mistral 7 B Instruct V0.3 | $0.100 | $0.100 |
| Mamba Codestral 7 B V0.1 | $0.190 | $0.190 |
| Llava V1.6 Mistral 7 B Hf | $0.290 | $0.290 |
| Meta Llama 3.1 70 B Instruct | $0.670 | $0.670 |
Compare against
- Mistral Small 3.2 24 B Instruct 2506 vs Qwen 3.6 35 B A3 B
- Mistral Small 3.2 24 B Instruct 2506 vs Qwen 3 235 B A22 B2507
Cheaper alternatives
Next cheaper option: Seed 1.6 Flash at $0.075 per 1M input tokens. Next step up: GPT OSS 120 B at $0.060 per 1M input tokens.