gpt-realtime-2.1
vercel/openai/gpt-realtime-2.1 · family gpt · in: text, audio → out: text, audio · price provider-declared (via models.dev). Capabilities: reasoning text audio.
$9.00
Blended $/1M (3:1)
$4
Input $/1M
$24
Output $/1M
$28.00
1M in + 1M out
$0.4 −90%
Cache read $/1M
#7020 of 7,708
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text, audio)
- Context
- 128,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- reasoning text audio
Same model, other providers
“gpt-realtime-2.1” 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) | $4 | $24 | $9.00 | 128k |
| OpenAI | $4 | $24 | $9.00 | 128k |
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-realtime-2.1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):