Mistral Small 4 pricing, context window and limits
Mistral Small 4 costs $0.15 per million input tokens and $0.6 per million output tokens at Mistral AI list price. It accepts up to 256,000 tokens of context and returns up to 256,000 tokens.
- Model id
mistral-small-2603 - Snapshot
What does Mistral Small 4 cost?
| Input | $0.15 |
|---|---|
| Output | $0.6 |
| Cached input (read) | $0.015 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Mistral Small 4 read and write?
| Context window | 256,000 |
|---|---|
| Max output | 256,000 |
What can Mistral Small 4 do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | Yes |
| Input | text, image |
| Output | text |
What does a request to Mistral Small 4 cost?
| A typical request: 1,000 tokens in, 500 out | $0.00045 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0021 |
| 1,000 typical requests | $0.45 |
| 1 million tokens in and 1 million out | $0.75 |
Input read from the provider's prompt cache costs $0.015 per million tokens instead of $0.15, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.00032 instead of $0.00045.
Among 32 Mistral AI models with a published price, Mistral Small 4 is the 9th cheapest by input price. Its context window is the 11th largest of 32. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Mistral Small 4 through DVARA?
Configure the mistral provider in the DVARA LLM Gateway and send the model id mistral-small-2603. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
Which other Mistral AI models are there?
- Mistral Small 3.2$0.1 in · $0.3 out · 128K context
- Mistral Small (latest)$0.15 in · $0.6 out · 256K context
- Mistral Nemo$0.15 in · $0.15 out · 128K context
- Mistral 7B$0.25 in · $0.25 out · 8K context
- Mistral Medium (latest)$1.5 in · $7.5 out · 262K context
- Mistral Medium 3.5$1.5 in · $7.5 out · 262K context
- Mistral Medium 3.1$0.4 in · $2 out · 262K context
- Mistral Medium 3$0.4 in · $2 out · 131K context
- Mistral Large (latest)$0.5 in · $1.5 out · 262K context
- Mistral Large 3$0.5 in · $1.5 out · 262K context
- Mistral Large 2.1$2 in · $6 out · 131K context
- Mistral Embed$0.1 in · $0 out · 8K context
Which models from other providers are similar to Mistral Small 4?
These are the closest in context window and input price, one per provider.
- NVIDIA Nemotron 3 Super 120B A12BAmazon Bedrock · $0.15 in · $0.65 out · 262K context
- Qwen3-VL PlusAlibaba Qwen · $0.1434 in · $1.4335 out · 262K context
- GPT OSS 120BGroq · $0.15 in · $0.6 out · 131K context
- Command RCohere · $0.15 in · $0.6 out · 128K context
- GPT-4o miniOpenAI · $0.15 in · $0.6 out · 128K context