apimartydv9/llm-api-proxy-migration-kit

token-billed: text_input $4/M, cached_text_input $1/M, image_input $8/M, cached_image_input $2/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 1 (gpt-image-1) through APIMart

• One key, entire catalog. The same https://api.apimart.ai/v1 base URL and Authorization header reach GPT Image 1 (gpt-image-1) 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.
• The charge comes back in the response. Every completed task reports the amount billed (cost / credits_cost); a task marked failed is refunded.
• Async by design. Submit, take the task_id, poll GET /v1/tasks/{id} — batching and retries are ordinary queue work, not a bespoke integration.

GPT Image 1 is OpenAI's image generation model served on APIMart with token-based billing and an OpenAI-compatible endpoint.

Endpoint: POST https://api.apimart.ai/v1/images/generations (OpenAI-compatible), then poll GET /v1/tasks/{task_id}.

Token rates (effective): text_input $4/M, cached_text_input $1/M, image_input $8/M, cached_image_input $2/M, image_output $32/M.

Prices are a snapshot; the pricing page and data/model.json are refreshed by CI, and a completed task reports the exact amount in its cost field.

The table lists the fields accepted by the APIMart OpenAI-compatible image endpoint. Check the model page for anything this model adds on top.

curl --request POST --url https://api.apimart.ai/v1/images/generations \
  --header "Authorization: Bearer $APIMART_API_KEY" --header 'Content-Type: application/json' \
  -d '{"model":"gpt-image-1","prompt":"A bamboo forest at sunrise, slow push-in","size":"1:1","resolution":"1K"}'

import os, time, requests

BASE = "https://api.apimart.ai/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}", "Content-Type": "application/json"}

created = requests.post(f"{BASE}/images/generations", headers=HEADERS, timeout=60, json={
    "model": "gpt-image-1", "prompt": "A bamboo forest at sunrise, slow push-in",
}).json()
task_id = created["data"]["id"]

while True:
    task = requests.get(f"{BASE}/tasks/{task_id}", headers=HEADERS, timeout=60).json()["data"]
    if task["status"] in ("completed", "failed"):
        break
    time.sleep(5)
print(task.get("cost"), task["result"]["images"][0]["url"])

Runnable versions: examples/. The task lifecycle is pending → processing → completed | failed.

What is the GPT Image 1 model id?

gpt-image-1. See the route table above.

How is it billed?

token-billed: text_input $4/M, cached_text_input $1/M, image_input $8/M, cached_image_input $2/M. The completed task reports the exact amount in its cost field; a failed task is refunded.

How do I get a key?

Use the Get an API key link — $1 minimum top-up, no plan required.

Outbound APIMart links are minted through the promo link API; hand-made tracking parameters are rejected by tools/check_links.py in CI.

GPT Image 1 is a third-party model served through APIMart; this repository documents how to call it and publishes model ids and prices, and does not claim official status. Model names, prices and documentation belong to their respective owners.

MIT — see LICENSE.