o1
vercel/openai/o1 · family o · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$26.25
Blended $/1M (3:1)
$15
Input $/1M
$60
Output $/1M
$75.00
1M in + 1M out
$7.5 −50%
Cache read $/1M
#7549 of 7,708
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 100,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“o1” is offered by 11 providers — cheapest-effective first. Poe is the cheapest at $24.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Poe | $14 | $54 | $24.00 | 200k |
| Vercel AI Gateway (this) | $15 | $60 | $26.25 | 200k |
| Kilo Gateway | $15 | $60 | $26.25 | 200k |
| OpenRouter | $15 | $60 | $26.25 | 200k |
| Azure | $15 | $60 | $26.25 | 200k |
| Azure Cognitive Services | $15 | $60 | $26.25 | 200k |
| Impossibl | $15 | $60 | $26.25 | 200k |
| Merge Gateway | $15 | $60 | $26.25 | 200k |
| Eden AI | $15 | $60 | $26.25 | 200k |
| DevPass (LLM Gateway) | $15 | $60 | $26.25 | 200k |
| OpenAI | $15 | $60 | $26.25 | 200k |
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/o1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):