KB Whisper
evroc/KBLab/kb-whisper-large · family whisper · in: audio → out: text · price provider-declared (via models.dev). Capabilities: audio.
$0.00
Blended $/1M (3:1)
$0.0023
Input $/1M
$0.0023
Output $/1M
$0.00
1M in + 1M out
—
Cache read $/1M
#600 of 7,710
Cheapest rank
- Provider
- evroc (
evroc) - Kind
- text (outputs text)
- Context
- 448 tokens
- Max output
- 448 tokens
- Capabilities
- audio
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":"KBLab/kb-whisper-large","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):