GPT Image 2
Next-gen image generation & editing with stronger compositional control and text rendering.
OpenAI$0.05 / imagetext-to-imageopenai
Capability
Est. cost$0.05For $1 you can run this model 20 times.
Example output
$0.05/ image
$0.05 per image. For $1 you can run this model 20 times.
Pay only for successful generations. No idle, no minimums, no per-seat.
API
Wire it up.
Endpoint
POST https://api.tryinfer.com/v1/inference/gpt-image-2/text-to-imagerequest
curl https://api.tryinfer.com/v1/inference/gpt-image-2/text-to-image \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "a watercolour illustration of a cat reading a book by candlelight"
}
}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| prompt | string | Yes | — | — |
| num_images | integer | — | 1 | — |
| aspect_ratio | string | — | 1:1 | 21:916:93:24:31:13:42:39:16 |
| output_format | string | — | png | jpegpngwebp |
Authenticate with a bearer token. Get an API key →
Further reading
From the Infer content directory.
Best ofBest AI models for text rendering and typographyIdeogram 3.0 is the typography specialist at $0.06/image; Nano Banana 2 claims near-Ideogram fidelity at half the latency for $0.039. Full 2026 ranking below.CompareFLUX 1.1 vs GPT Image 1.5: speed vs smartsGPT Image 1.5 wins on quality (1271 Elo, +12% photorealism vs FLUX). FLUX 1.1 wins on throughput: ~2.5s vs ~5s, at half the price or less. Full breakdown.Best ofBest AI models for product photography in 2026Imagen 4 wins clean catalog shots, GPT Image 1.5 handles lifestyle staging, FLUX Kontext swaps backgrounds, and SAM 3.1 cuts out products at scale in 2026.