Mistral Small 4
Pricing updated daily · Last refreshed Oct 30, 2026Mistral model with a 262K-token context window, priced at $0.15 per million input tokens and $0.60 per million output tokens.
At a glance
- Provider
- Mistral
- Context window
- 262,144 tokens
- Max output
- 209,715 tokens
- Input price
- $0.15 / 1M tokens
- Output price
- $0.60 / 1M tokens
- Input types
- text, image
- Function calling
- Yes
- Released
- March 16, 2026
What it costs
Illustrative request sizes, not measurements of any real product. For your own volumes, use the cost estimator.
| Workload | Tokens in / out | Per request | Per 1,000 requests |
|---|---|---|---|
| Short chat reply | 1,000 / 500 | $0.000450 | $0.4500 |
| Question over retrieved documents | 8,000 / 500 | $0.0015 | $1.50 |
| Summarise a long document | 50,000 / 1,500 | $0.0084 | $8.40 |
How it compares
- Input price ($0.15 per 1M tokens) is the 7th lowest of 30 models in the catalogue.
- Output price ($0.60 per 1M tokens) is the 9th lowest of 30.
- Context window (262K tokens) is the 18th largest of 30.
- Maximum output (210K tokens) is the 3rd largest of 30.
- On blended price it is 67% cheaper than the median Mistral model in the catalogue.
These are rankings by listed price and size within this catalogue (blended price weights input 3:1 against output), not a measure of output quality.
Cheaper models with the same capabilities
Lower blended price, at least the same context window, and the same input types and function calling.
| Model | Provider | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|
| Llama 4 Scout | Meta | 1.31M | $0.10 | $0.30 |
| Claude Haiku 5.5 | Anthropic | 1M | $0.10 | $0.50 |
| GPT-6 Luna Pro | OpenAI | 1.05M | $0.10 | $0.50 |
More from Mistral
| Model | Provider | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|
| Mistral Large 4 | Mistral | 1.05M | $0.70 | $2.10 |
| Mistral Medium 3.5 | Mistral | 262K | $1.50 | $7.50 |
| Devstral 2 2512 | Mistral | 262K | $0.40 | $2.00 |
| Ministral 3 14B 2512 | Mistral | 262K | $0.20 | $0.20 |
Try it with your own text
- Token counter: see how many tokens a prompt uses (exact for OpenAI models, labelled estimates for others).
- Context window visualizer: see how much of this model’s 262K window a prompt fills.
- Model comparison: sort and filter every model, and export to CSV.
Source: OpenRouter’s public model catalogue (mistralai/mistral-small-2603), read once a day. These are the prices OpenRouter charges; a provider’s own list price can differ, so check the provider before committing to a budget.