Voxtral Small
As of Nov 22, 2026, the cheapest Voxtral Small API price is $0.1 per 1M input tokens (LLMTR) and $0.3 per 1M output tokens (LLMTR). Voxtral Small is offered by 3 providers in the voxtral-small family, open weights. Mistral's own rate is $0.4 per 1M output tokens.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| LLMTRopenmistral/voxtral-small-latest | Cheapest$0.1 | Cheapest$0.3 | — | — | 32k | — |
| Eden AIopenmistral/voxtral-small-latest | $0.1 | $0.4 | $0.01 | — | 33k | — |
| Mistralopenvoxtral-small-2507 | $0.1 | $0.4 | — | — | 33k | — |
| Mistralopenvoxtral-small-latest | $0.1 | $0.4 | — | — | 33k | 33d ago |
| Eden AIopenmistral/voxtral-small-latest@eu | $0.11 | $0.44 | $0.011 | — | 33k | — |
Voxtral Small price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Mistral | $0.1 | $0.3 → $0.4 | +33.3% |
Voxtral Small pricing FAQ
What is the cheapest Voxtral Small API?
As of Nov 22, 2026, LLMTR has the lowest Voxtral Small output price at $0.3 per 1M tokens, and LLMTR has the lowest input price at $0.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How much does Voxtral Small cost on Mistral?
Mistral charges $0.1 per 1M input tokens and $0.4 per 1M output tokens for Voxtral Small.
How many providers offer Voxtral Small?
3 providers list Voxtral Small on Sovyron; 5 of them sell it at a metered per-token price.
Is Voxtral Small free?
No provider in the Sovyron catalog lists a free tier for Voxtral Small.
What is the context window of Voxtral Small?
Voxtral Small supports a 33k-token context window and up to 32k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—