Devstral Small pricing
Source: litellm · updated 2026-11-18
Short answer: Devstral Small costs $0.070 per million input tokens and $0.280 per million output tokens. That is a 3:1 blended rate of $0.122 per million tokens, ranking it #112 of 833 tracked models by input price.
Input / 1M
$0.070
Output / 1M
$0.280
Output ÷ input
4.00×
Context window
128,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.070 |
| Output, per 1M tokens | $0.280 |
| Output ÷ input multiple | 4.00× |
| 3:1 blended, per 1M tokens | $0.122 |
| Context window | 128,000 tokens |
| Vendor | vercel_ai_gateway |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.070 | $0.070 | $0.140 |
| 10M in / 2.5M out | $0.700 | $0.700 | $1.40 |
| 100M in / 25M out | $7.00 | $7.00 | $14.00 |
Other vercel_ai_gateway models
| Model | Input | Output |
|---|---|---|
| Ministral 3 B | $0.040 | $0.040 |
| Llama 3.8 B | $0.050 | $0.080 |
| Qwen 3 14 B | $0.080 | $0.240 |
| Qwen 3 30 B | $0.100 | $0.300 |
| Qwen 3 32 B | $0.100 | $0.300 |
Compare against
Cheaper alternatives
Next cheaper option: Llama 3.2.3 B Instruct at $0.051 per 1M input tokens. Next step up: Us Gov Nvidia Nemotron Nano 9 B at $0.072 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.