Voxtral Small (latest)
tempr/mistral/voxtral-small-latest · family voxtral · in: text, audio → out: text · price provider-declared (via models.dev). Capabilities: tools text audio.
$0.18
Blended $/1M (3:1)
$0.1
Input $/1M
$0.4
Output $/1M
$0.50
1M in + 1M out
—
Cache read $/1M
#1550 of 8,512
Cheapest rank
- Provider
- Tempr Gateway (
tempr) - Kind
- text (outputs text)
- Context
- 32,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- tools text audio
Same model, other providers
“Voxtral Small (latest)” is offered by 4 providers — cheapest-effective first. LLMTR is the cheapest at $0.15 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| LLMTR | $0.1 | $0.3 | $0.15 | 32k |
| Tempr Gateway (this) | $0.1 | $0.4 | $0.18 | 32k |
| Eden AI | $0.1 | $0.4 | $0.18 | 33k |
| Mistral | $0.1 | $0.4 | $0.18 | 33k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Tempr Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistral/voxtral-small-latest","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):