Mistral: Voxtral Small 24B 2507
by Mistral AIMistral: Voxtral Small 24B 2507 is a large language model from Mistral AI. It costs $0.100 per million input tokens and $0.300 per million output tokens. Its context window is 33K tokens.
- Input / 1M tokens
- $0.100
- Output / 1M tokens
- $0.300
- Cached input / 1M
- $0.010
- Context window
- 33K
On repeated prefixes
tokens
Who serves it cheapest
1 hosts serve Voxtral Small 24B 2507. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| MistralCheapest | $0.100 | $0.300 | 33K | - | 99.6% |
About Voxtral Small 24B 2507
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...
Specifications
| Model ID | mistralai/voxtral-small-24b-2507 |
|---|---|
| Provider | Mistral AI |
| Context window | 33K tokens |
| Max output | 26K tokens |
| Input modalities | text, audio, file |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - mistralai/Voxtral-Small-24B-2507 |
| Released | October 30, 2025 |
Cheaper alternatives
Models that cost less than Voxtral Small 24B 2507 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Mistral: Voxtral Small 24B 2507 cost?
$0.100 per million input tokens and $0.300 per million output tokens. Cached input reads cost $0.010 per million tokens.
What is the context window of Mistral: Voxtral Small 24B 2507?
33K tokens, with up to 26K tokens of output per request.
Confirm against the source: Mistral AI official pricing.