Image generation

One workflow for every available image model: choose a model, send a request, read the response, and understand the price.

Available image models

0.5K

$0.045 / image

1K

$0.067 / image

2K

$0.101 / image

4K

$0.151 / image

image input

$8.00 / 1M tokens

cached image input

$2.00 / 1M tokens

generated image output

$30.00 / 1M tokens

image input

$8.00 / 1M tokens

cached image input

$2.00 / 1M tokens

generated image output

$30.00 / 1M tokens

per generation request

$0.02 / image

1K

$0.06 / image

2K

$0.08 / image

image input

$2.00 / 1M tokens

generated image output

$120.00 / 1M tokens

image input

$2.00 / 1M tokens

generated image output

$120.00 / 1M tokens

image input

$0.50 / 1M tokens

generated image output

$60.00 / 1M tokens

Request

POST /v1/images/generations. The path and optional parameters come from the selected model’s verified contract.

curl -sS https://api.oneprovider.dev/v1/images/generations \
-H "Authorization: Bearer $ONEPROVIDER_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A quiet observatory above the clouds",
"size": "1024x1024",
"quality": "low"
}'

Capabilities vary by model

Sizes, quality levels, transparency, editing, and response formats are model-specific. Do not copy one model’s optional parameters to another without checking support.

Response

A synchronous transport returns image data or a URL immediately. An asynchronous transport returns a job id; poll its status path, then download from its content path.

Pricing

The shared model table separates every token rate into its own column and shows per-image or other media billing in the media column. Open pricing .

Quick answers

Which base URL do I use?

Claude Code and Anthropic SDKs use https://api.oneprovider.dev. OpenAI SDKs and OpenAI-compatible clients use https://api.oneprovider.dev/v1. One key works behind both; the model list is on the models page ; rates are on the pricing page .

How do I authenticate?

Send the raw sk-… key in x-api-key or Authorization: Bearer: one of them, never both. Keep the key in an environment variable, not in a file that gets committed. More on authentication .

Where do I get a key?

Open your cabinet in the Telegram bot @oneprovider_robot or at app.oneprovider.dev, top up the balance and press “Issue a key”. Each key can carry its own spend limit. Cabinet & API keys .

What do 401, 404 and 429 mean?

401: the key is missing, mistyped or sent in the wrong header; paste the whole key without quotes or spaces. 404: usually a wrong base URL, for example a missing or doubled /v1. 429 with “Insufficient balance”: the cabinet balance or the key’s spend limit is used up, so top up instead of retrying; any other 429 is a rate limit, so wait for Retry-After. Details: error codes and troubleshooting .

Why do streams cut off or reset?

VPN and VLESS proxies often buffer SSE or break HTTP/2 negotiation. OneProvider has no regional restrictions and does not buffer streams, so turn the proxy off and retry.

Where do I ask if this is not enough?

Message @Oneproviderhelpbot on Telegram or open “Support” in the web cabinet, with the HTTP status code and the exact error message. How support works .