GPT Image 2.6 Fast
GPT Image 2.6 Fast is the generation variant of OpenAI's GPT Image 2.6 pair, built for making images from a text prompt quickly. It carries five detail levels. At the high level, the one the listed price names, it bills what GPT Image 2.5 does at every size; its two lowest levels cost more than 2.5's, with a draft at about two cents a square image instead of under one. Billing follows the tokens it actually renders, so you pay the measured amount rather than a flat rate. The listed price is one standard square image at the high level. It also accepts reference images, which guide the result.
Pricing
Input
$0.053 / image
Output
—
Pay only for what you use. No subscriptions, no monthly minimum.
Specs
- Context
- —
- Max output
- 4 images
- Latency
- Medium
- Category
- Image
Constraints & limits
Output
Presigned URLs (~24h TTL)
The gateway auto-clamps requests to the model's limits where possible.
Quick start
This sample hits the image generation endpoint. Change base_url and your key, then run it.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.images.generate(
model="openai/gpt-image-2.6-fast",
prompt="A futuristic city skyline at sunset.",
size="1024x1024",
n=1,
)
print(response.data[0].url)Similar models
GPT Image 2.6 Precise
The editing half of GPT Image 2.6. Give it up to four images and a prompt, and it changes what you asked for and leaves the rest alone, at all five detail levels.
GPT Image 2.5 Fast
The quick half of GPT Image 2.5. Five detail levels, from a cent-scale draft to a finished frame, billed on what it actually renders.