Voxtral Small 24B

evroc/mistralai/Voxtral-Small-24B-2507 · family voxtral · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: audiotext.

$0.00Blended $/1M (3:1)

$0.0023Input $/1M

$0.0023Output $/1M

$0.001M in + 1M out

—Cache read $/1M

#490 of 5,000Cheapest rank

Provider: evroc (evroc)
Context: 32,000 tokens
Max output: 32,000 tokens
Capabilities: audiotext

Same model, other providers

“Voxtral Small 24B” is offered by 2 providers — cheapest-effective first. This one (evroc) is the cheapest.

Provider	Input	Output	Blended	Context
evroc (this)	$0.0023	$0.0023	$0.00	32k
GreenPT	$0.228	$0.513	$0.30	33k

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):