Voxtral Small 24B
evroc/mistralai/Voxtral-Small-24B-2507 · family voxtral · in: audio, text → out: text · price provider-declared (via models.dev). Capabilities: audio text.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See evroc’s docs for per-unit rates.
- Provider
- evroc (
evroc) - Kind
- text (outputs text)
- Context
- 32,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- audio text
Same model, other providers
“Voxtral Small 24B” is offered by 2 providers — cheapest-effective first. GreenPT is the cheapest at $0.30 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| GreenPT | $0.228 | $0.513 | $0.30 | 33k |
| evroc (this) | — | — | — | 32k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at evroc and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistralai/Voxtral-Small-24B-2507","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):