Whisper Large v3

scaleway/whisper-large-v3 · family whisper · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: audio.

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

$0.003Input $/1M

freeOutput $/1M

$0.001M in + 1M out

—Cache read $/1M

#489 of 5,000Cheapest rank

Provider: Scaleway (scaleway)
Context: 0 tokens
Max output: 8,192 tokens
Capabilities: audio

Same model, other providers

“Whisper Large v3” is offered by 3 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	0
Scaleway (this)	$0.003	free	$0.00	0
NEAR AI Cloud	$0.01	free	$0.01	448

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Scaleway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"whisper-large-v3","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):