Images

Generate image

OpenAI-compatible image generation. Model-agnostic — works with Volcano Engine Seedream, Bailian qwen-image, OpenAI gpt-image, and others. The gateway forwards only the fields listed below and ignores the rest; values such as size are validated by the upstream model.

POST/v1/images/generations

Key request parameters

Parameter	Type	Description
`model`	string · Required	Model identifier, e.g. `doubao-seedream-5-0-pro-260628` / `qwen-image-plus` / `gpt-image-2`
`prompt`	string · Required	Text prompt
`n`	integer	Number of images; default 1
`size`	string	Size preset (e.g. `2K`) or `WxH` (e.g. `2048x2048`); supported values depend on the model
`response_format`	enum	`url` (default) \| `b64_json`
`watermark`	boolean	Whether to add a watermark (Doubao / Volcano Engine only)
`user`	string	End-user identifier for abuse tracking

Key response parameters

Parameter	Type	Description
`created`	integer	Unix timestamp (seconds)
`data[].url`	string	Returned when `response_format=url`
`data[].b64_json`	string	Returned when `response_format=b64_json`
`data[].revised_prompt`	string	Model-revised prompt, if any
`data[].size`	string	Actual size of the generated image
`usage.generated_images`	integer	Number of images generated
`usage.output_tokens`	integer	Image tokens counted toward billing
`usage.total_tokens`	integer	Sum

Integration examples

Replace the API key and model ID in these examples with your values.

cURL

curl https://hashbidx.ai/v1/images/generations \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-0-pro-260628",
    "prompt": "interstellar, a black hole, a shattered vintage train bursting out of it, cinematic",
    "size": "2K",
    "response_format": "url",
    "watermark": false
  }'

Python

import httpx

resp = httpx.post(
    "https://hashbidx.ai/v1/images/generations",
    headers={"Authorization": "Bearer <YOUR_API_KEY>"},
    json={
        "model": "doubao-seedream-5-0-pro-260628",
        "prompt": "a cat playing piano, cinematic lighting",
        "size": "2K",
        "response_format": "url",
        "watermark": False,
    },
)
resp.raise_for_status()
print(resp.json())

Node.js

const resp = await fetch("https://hashbidx.ai/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "doubao-seedream-5-0-pro-260628",
    prompt: "a cat playing piano, cinematic lighting",
    size: "2K",
    response_format: "url",
    watermark: false,
  }),
});
console.log(await resp.json());

body, _ := json.Marshal(map[string]any{
  "model":          "doubao-seedream-5-0-pro-260628",
  "prompt":         "a cat playing piano, cinematic lighting",
  "size":           "2K",
  "response_format": "url",
  "watermark":      false,
})
req, _ := http.NewRequest("POST",
  "https://hashbidx.ai/v1/images/generations", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer <YOUR_API_KEY>")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)

Rust

let body = serde_json::json!({
    "model": "doubao-seedream-5-0-pro-260628",
    "prompt": "a cat playing piano, cinematic lighting",
    "size": "2K",
    "response_format": "url",
    "watermark": false,
});
let resp = reqwest::Client::new()
    .post("https://hashbidx.ai/v1/images/generations")
    .bearer_auth("<YOUR_API_KEY>")
    .json(&body)
    .send().await?;

If the response includes X-Request-Id, include it when troubleshooting an issue.

All API endpoints

BUILD WITH HASHBIDX

Find your model. Make your first call.

Models & pricing