GPT-4o Transcribe
vercel/openai/gpt-4o-transcribe · family gpt · in: audio → out: text · price provider-declared (via models.dev). Capabilities: audio.
$4.38
Blended $/1M (3:1)
$2.5
Input $/1M
$10
Output $/1M
$12.50
1M in + 1M out
—
Cache read $/1M
#6341 of 7,708
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 0 tokens
- Max output
- 0 tokens
- Capabilities
- audio
Same model, other providers
“GPT-4o Transcribe” is offered by 2 providers — cheapest-effective first. This one (Vercel AI Gateway) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vercel AI Gateway (this) | $2.5 | $10 | $4.38 | 0 |
| DevPass (LLM Gateway) | $2.5 | $10 | $4.38 | 16k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4o-transcribe","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):