GPT-5-nano
poe/openai/gpt-5-nano · family gpt-nano · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.12
Blended $/1M (3:1)
$0.045
Input $/1M
$0.36
Output $/1M
$0.40
1M in + 1M out
$0.0045 −90%
Cache read $/1M
#1078 of 7,708
Cheapest rank
- Provider
- Poe (
poe) - 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 3 providers — cheapest-effective first. This one (Poe) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Poe (this) | $0.045 | $0.36 | $0.12 | 400k |
| Jiekou.AI | $0.045 | $0.36 | $0.12 | 400k |
| SAP AI Core | $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 Poe 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):