GPT Image 2 (official) API (gpt-image-2-official)

token-billed: text_input $4/M, cached_text_input $1/M, image_input $6.4/M, cached_image_input $1.6/M — one OpenAI-compatible endpoint at https://api.apimart.ai/v1, no monthly plan required. (observed 2026-10-12)

Get an API key · Live pricing · Model page · ⚡ 60-second quickstart

Why teams call GPT Image 2 (official) (gpt-image-2-official) through APIMart

• One key, entire catalog. The same https://api.apimart.ai/v1 base URL and Authorization header reach GPT Image 2 (official) (gpt-image-2-official) and 300+ other image, video and language models — switch the model field, not your client.
• $1 minimum, pay as you go. No subscription and no prepaid plan to size up front: top up from $1 and spend it on calls. There is no free quota to burn through first, so the price in this table is the price you pay.
• The charge comes back in the response. Every completed task reports the amount billed (cost / credits_cost), so a spend number is read per call instead of guessed at month end.
• Async by design. Submit, take the task_id, poll GET /v1/tasks/{id} — batching and retries are ordinary queue work, not a bespoke integration.

Published unit prices (snapshot 2026-09-28)

Unit	Price
GPT Image 2.5 (1K)	$0.0085
Seedance 2.0 Mini (480P/sec)	$0.01056
Qwen3.7 Flash (per M input)	$0.0228568

Quickstart

curl -X POST https://api.apimart.ai/v1/images/generations \
  -H 'Authorization: Bearer $APIMART_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model":"gpt-image-2.5-ext","prompt":"cozy reading nook, warm lamp, cinematic","size":"1:1","resolution":"1K","n":1}'

Async: submit → get task_id → poll GET https://api.apimart.ai/v1/tasks/<task_id> → read cost / credits_cost from the result. Parameter tables, version/resolution/size options and idempotency headers are documented on the model page reachable from the pricing link above.

Keywords

rétro-ingénierie · reverse-engineered · passerelle API · relais API · nano banana 2 api · gpt-image-2.5 api · ai api pricing · pay-as-you-go

Platform facts

• USD settlement, pay-as-you-go, $1 minimum top-up, no subscription.
• Operating since last year; ~100,000 registered users, mostly enterprise accounts.
• International invoices available on request.
• 307 models online (live /v1/models) as of 2026-09-28.

Disclosure

This repository documents APIMart, a third-party API aggregator/gateway. It is not affiliated with, endorsed by, or sponsored by OpenAI, Google, Anthropic, xAI, ByteDance or any model vendor. Model names and trademarks belong to their owners. Prices are a point-in-time snapshot and may change; the vendor's console billing is authoritative.