GPT-Image-2 image
kenari/gpt-image-2 · family gpt-image · in: text, image → out: image · price provider-declared (via models.dev). Capabilities: text image.
This is an image model — providers price it per image, not per token, so models.dev carries no token price (fields read “—”). See Kenari’s docs for per-unit rates.
- Provider
- Kenari (
kenari) - Kind
- image (outputs image)
- Context
- 272,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- text image
Same model, other providers
“GPT-Image-2” is offered by 4 providers — cheapest-effective first. OpenAI is the cheapest at $11.25 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenAI | $5 | $30 | $11.25 | 0 |
| Azure | $5 | $30 | $11.25 | 0 |
| Poe | $5.05 | $32.32 | $11.87 | 0 |
| Kenari (this) | — | — | — | 272k |
Call it
jishie indexes & prices models; it does not proxy inference.
Image generation — call Kenari’s image endpoint with this model id:
curl $BASE_URL/v1/images/generations \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gpt-image-2","prompt":"a red bicycle"}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):