GPT-5 Nano
vercel/openai/gpt-5-nano · family gpt-nano · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.14
Blended $/1M (3:1)
$0.05
Input $/1M
$0.4
Output $/1M
$0.45
1M in + 1M out
$0.005 −90%
Cache read $/1M
#1191 of 7,713
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 400,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“GPT-5 Nano” is offered by 22 providers — cheapest-effective first. Ofox is the cheapest at $0.11 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Ofox | $0.04 | $0.32 | $0.11 | 400k |
| Vercel AI Gateway (this) | $0.05 | $0.4 | $0.14 | 400k |
| NEAR AI Cloud | $0.05 | $0.4 | $0.14 | 400k |
| Databricks | $0.05 | $0.4 | $0.14 | 400k |
| Kilo Gateway | $0.05 | $0.4 | $0.14 | 400k |
| Abacus | $0.05 | $0.4 | $0.14 | 400k |
| OpenRouter | $0.05 | $0.4 | $0.14 | 400k |
| Azure | $0.05 | $0.4 | $0.14 | 400k |
| Azure Cognitive Services | $0.05 | $0.4 | $0.14 | 400k |
| Impossibl | $0.05 | $0.4 | $0.14 | 400k |
| Cloudflare AI Gateway | $0.05 | $0.4 | $0.14 | 128k |
| FastRouter | $0.05 | $0.4 | $0.14 | 400k |
| OrcaRouter | $0.05 | $0.4 | $0.14 | 400k |
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-5-nano","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):