Best Input Price
$0.10 / 1M
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
Context Window
128,000 tokens
Reasoning
No
Tool Calling
Supported
Released
2025-07-15
Inference Providers (5)
| Provider | Model ID | Context | Input / 1M | Output / 1M | Action |
|---|---|---|---|---|---|
| Kilo Gateway | mistralai/voxtral-small-24b-2507 | 32,768 | $0.10 | $0.30 | Docs ↗ |
| OpenRouter | mistralai/voxtral-small-24b-2507 | 32,768 | $0.10 | $0.30 | Docs ↗ |
| Eden AI | amazon/mistral.voxtral-small-24b-2507 | 128,000 | $0.10 | $0.30 | Docs ↗ |
| Amazon Bedrock | mistral.voxtral-small-24b-2507 | 32,768 | $0.10 | $0.30 | Docs ↗ |
| GreenPT | voxtral-small-24b-2507 | 32,768 | $0.23 | $0.51 | Docs ↗ |