Mistral AI · open weights
Mistral Small 4 API pricing by provider
Mistral Small 4 is available from 2 providers. The cheapest is Mistral at $0.15 input / $0.60 output per 1M tokens. The priciest host, Venice, charges 1.3x the cheapest.
Prices from the OpenRouter API, retrieved September 15, 2026. Weights: mistralai/Mistral-Small-4-119B-2603.
| Provider | Precision | Input / 1M | Output / 1M | Document Q&A / month | Context | Max output |
|---|---|---|---|---|---|---|
| Mistralcreator | — | $0.15 | $0.60 | $78.00 | 262K | 210K |
| Mistral | — | $0.165 | $0.66 | $85.80 | 262K | 210K |
| Venice | fp8 | $0.1875 | $0.75 | $97.50 | 256K | 66K |
Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.
Frequently asked questions
- What is the cheapest Mistral Small 4 API provider?
- Mistral is the cheapest healthy provider we track at $0.15 per 1M input tokens and $0.60 per 1M output tokens.
- How much does Mistral Small 4 cost?
- Across 2 providers, input prices range from $0.15 to $0.1875 per 1M tokens and output prices from $0.60 to $0.75.
- What is Mistral Small 4’s context window?
- Mistral Small 4 supports up to 262K tokens, but some providers serve a smaller context window — check the table before choosing.
Other open-weight models
- DeepSeek V4.1 Flashfrom $0.15 / $0.60
- DeepSeek V4 Pro 0813from $0.96 / $2.88
- Kimi K3from $2.10 / $10.95
- GLM 5.3from $0.91 / $2.86
- GLM 5.3 Flashfrom $0.075 / $0.25
- Qwen3.8 27Bfrom $0.15 / $2.00
- MiniMax M3from $0.23 / $0.96
- gpt-oss-120bfrom $0.03 / $0.17
- gpt-oss-20bfrom $0.02 / $0.10
- Llama 4 Maverickfrom $0.1875 / $0.6525
- Llama 3.3 70B Instructfrom $0.10 / $0.32
- Gemma 4 31Bfrom $0.09 / $0.34
- Nemotron 3 Superfrom $0.085 / $0.40