Voxtral Small pricing, context window and limits
Voxtral Small costs $0.1 per million input tokens and $0.4 per million output tokens at Mistral AI list price. It accepts up to 32,768 tokens of context and returns up to 32,000 tokens.
- Model id
voxtral-small-2507 - Snapshot
What does Voxtral Small cost?
| Input | $0.1 |
|---|---|
| Output | $0.4 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Voxtral Small read and write?
| Context window | 32,768 |
|---|---|
| Max output | 32,000 |
What can Voxtral Small do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text, audio |
| Output | text |
What does a request to Voxtral Small cost?
| A typical request: 1,000 tokens in, 500 out | $0.0003 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0014 |
| 1,000 typical requests | $0.3 |
| 1 million tokens in and 1 million out | $0.5 |
Among 40 Mistral AI models with a published price, Voxtral Small is the 4th cheapest by input price. Its context window is the 36th largest of 40. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Voxtral Small through DVARA?
Configure the mistral provider in the DVARA LLM Gateway and send the model id voxtral-small-2507. DVARA, the AI gateway, 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 gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Mistral AI models are there?
- Voxtral Mini TTS (latest)— in · — out · — context
- Voxtral Small (latest)$0.1 in · $0.3 out · 33K context
- Voxtral Mini (latest)— in · — out · — context
- GLM-5.2$1.4 in · $4.4 out · 1.05M context
- Pixtral Large (latest)$2 in · $6 out · 128K context
- GLM-5.3$1.4 in · $4.4 out · 1.05M context
- Pixtral 12B$0.15 in · $0.15 out · 128K context
- Mixtral 8x7B$0.7 in · $0.7 out · 32K context
- Mixtral 8x22B$2 in · $6 out · 64K context
- Open Mistral Nemo$0.15 in · $0.15 out · 128K context
- Mistral 7B$0.25 in · $0.25 out · 8K context
- Mistral Small (latest)$0.15 in · $0.6 out · 262K context
Which models from other providers are similar to Voxtral Small?
These are the closest in context window and input price, one per provider.
- Voxtral Small 24B 2507Amazon Bedrock · $0.1 in · $0.3 out · 33K context
- Qwen2.5-Omni 7BAlibaba Qwen · $0.087 in · $0.345 out · 33K context
- Nano BananaGoogle Gemini · $0.3 in · $30 out · 33K context
- text-embedding-ada-002OpenAI · $0.1 in · $0 out · 8K context
- GPT OSS 20BGroq · $0.075 in · $0.3 out · 131K context