Back to models
Try in Studio
Model · OpenAI
GPT Image 2.6 Flare
openai/gpt-image-2.6-flare
Animated GIFs up to 16 frames, and world-knowledge edits and instructions; faster than Sunburst.
editreference imagesmask inpaintingcustom sizetransparent outputgif
Specs
Provider
OpenAI
Kind
Image
Pricing
$0.024–$0.228 / image
Endpoint
/api/v1/studio/image/generate
Providers and pricing
| Order | Provider | List price | Our price | Notes |
|---|---|---|---|---|
| 1 | Vercel AI Gateway | $0.019–$0.178 / image | $0.024–$0.228 / image | — |
| 2 | fal | $0.019–$0.178 / image | $0.024–$0.228 / image | — |
| Tier | Vercel AI Gateway | fal |
|---|---|---|
| low | $0.032list $0.025 | $0.032list $0.025 |
| medium | $0.056list $0.044 | $0.056list $0.044 |
| high | $0.068list $0.053 | $0.068list $0.053 |
| low-1080p | $0.024list $0.019 | $0.024list $0.019 |
| medium-1080p | $0.044list $0.034 | $0.044list $0.034 |
| high-1080p | $0.051list $0.040 | $0.051list $0.040 |
| low-1440p | $0.033list $0.026 | $0.033list $0.026 |
| medium-1440p | $0.061list $0.048 | $0.061list $0.048 |
| high-1440p | $0.071list $0.055 | $0.071list $0.055 |
| low-2160p | $0.060list $0.047 | $0.060list $0.047 |
| medium-2160p | $0.110list $0.086 | $0.110list $0.086 |
| high-2160p | $0.128list $0.100 | $0.128list $0.100 |
| low-gif-small | $0.045list $0.035 | $0.045list $0.035 |
| medium-gif-small | $0.080list $0.063 | $0.080list $0.063 |
| high-gif-small | $0.097list $0.076 | $0.097list $0.076 |
| low-gif-medium | $0.064list $0.050 | $0.064list $0.050 |
| medium-gif-medium | $0.113list $0.089 | $0.113list $0.089 |
| high-gif-medium | $0.137list $0.107 | $0.137list $0.107 |
| low-gif-large | $0.107list $0.083 | $0.107list $0.083 |
| medium-gif-large | $0.188list $0.147 | $0.188list $0.147 |
| high-gif-large | $0.228list $0.178 | $0.228list $0.178 |
Each request goes to the cheapest provider that can run it at the tier you ask for (highlighted); on a tie, Vercel AI Gateway first, then fal, then Atlas Cloud. If that provider fails on its side, the next one takes the request. You pay the list price of the provider that ran it, plus 28%.
Live performance
Loading measurements…
How we measure. Every request is timed from the moment we send it. A finish time comes from the provider's own timestamps when it reports them, from the moment it calls us back when it doesn't, and otherwise from polling: we take the midpoint between the last check that found the job running and the first that found it done, so it is off by at most half the poll interval. Requests you stop are left out. Figures appear once a window has 20 completed requests, and are aggregate only.
Code
curl https://terramind.com/api/v1/studio/image/generate \
-H "Authorization: Bearer $TERRAMIND_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.6-flare",
"prompt": "An astronaut riding a horse, photorealistic"
}'
Want to run this in your app? Grab an API key · Image API reference
More by OpenAI
| Model | Context | In | Out | Capabilities |
|---|---|---|---|---|
 openai/gpt-4o | 128K | $2.50 | $10.00 | visionaudiocaching |
| openai/gpt-5-mini | 400K | $0.250 | $2.00 | reasoningvisioncaching |
| openai/gpt-oss-20b | 131K | $0.080 | $0.300 | reasoning |
| openai/gpt-5.2 | 400K | $1.75 | $14.00 | reasoningvisioncaching |
| openai/gpt-5.4 | 1.1M | $2.50 | $15.00 | reasoningvisioncaching |
| openai/gpt-5.4-pro | 1.1M | $30.00 | $180.00 | reasoningvision |
| openai/gpt-5.5 | 1M | $5.00 | $30.00 | reasoningvisioncaching |
| openai/gpt-5.5-pro | 1M | $30.00 | $180.00 | reasoningvision |