What image formats and resolutions does gpt-image-2 support?

Confirm the current supported input and output image formats and resolution limits in the model documentation. Test with your specific image requirements before production use.

What is the max output length for gpt-image-2?

gpt-image-2 does not expose a token-based output limit. Image output is bounded by the supported sizes and the number of images you request; check the model page for current limits.

When was GPT-Image-2 released, and is it still maintained?

GPT-Image-2 is listed with catalog status stable. The recorded release date is 2026-04-21. Check the model page for deprecation notices before you build a long-lived integration on it.

Can gpt-image-2 edit existing images?

Yes. gpt-image-2 supports both image generation and editing via the dedicated Images API. Test your specific editing workflows to confirm compatibility.

How should you set the output budget for gpt-image-2?

For gpt-image-2, set the max_tokens or max_completion_tokens parameter to control spending per call. Start with a budget aligned to your typical response length and increase only when longer outputs are genuinely needed. Monitor token usage in the API response headers to tune your budget over time.

How many images can GPT-Image-2 generate per request?

GPT-Image-2 returns up to 10 images per request.

Can you call GPT-Image-2 with the OpenAI SDK you already use?

Yes. GPT-Image-2 is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to gpt-image-2 . Keep your current request and response handling.

Model detail

GPT-Image-2

Provided by OpenAI

Pay-as-you-go

OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.

Model specs

Model ID: gpt-image-2

Context length: –
Max output: –
I/O modalities
Released: 2026-06

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$5.0000 /1M Tokens

Completion

$30.0000 /1M Tokens

Cache read

$1.2500 /1M Tokens

Image input

$8.0000 /1M Tokens

Image completion

$5.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

OpenAI's latest image generation model

OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.

What should you check before using it?

Confirm output sizes and supported image formats

GPT-Image-2 supports streaming, prompt caching, vision input and the OpenAI SDK. Released 2026-04-21. The image input price is $8.0000 per 1M tokens. Test a representative workload before production.

Why use it through MixRoute?

GPT-Image-2 cache reads cut repeated-prompt cost

Cached prefixes are billed at $1.2500 per 1M tokens instead of $5.0000 per 1M tokens for standard input, so repeated system prompts cost less. MixRoute serves GPT-Image-2 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-image-2 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Streaming

GPT-Image-2 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

GPT-Image-2 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

Vision input

GPT-Image-2 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

OpenAI SDK

Call GPT-Image-2 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens

Output tokens

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

Use the model ID gpt-image-2 through the compatible Images API endpoint. Check the current API documentation for the exact endpoint path and required parameters.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

gpt-image-2

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs