Create generations — POST /v1/images/generations

Implements POST /v1/images/generations (OpenAI-compatible).

POST /v1/images/generations

AI → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/images/generations`
Method	`POST`
Operation	`post_images_generations`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Implements POST /v1/images/generations (OpenAI-compatible).

Body: {"model": "...", "prompt": "...", "n"?: int, "size"?: "1024x1024",

"response_format"?: "url"|"b64_json"}

It authenticates the caller, resolves the model to its upstream provider via the shared routing table (zen3-image* → do-ai fal diffusion), reserves the per-image budget, generates the image(s) through the do-ai async image client, records usage for billing, and returns the OpenAI images response.

Request

The document declares no body for POST /v1/images/generations. The handler is typed in cloud but its shape is not yet emitted, so the fields are not listed here — ask MCP's describe for post_images_generations, which answers from the running route.

Response

Status	Body	Meaning
`200`	openai.ImageResponse	Success.
`401`	—	No credential, or one this service does not accept.
`403`	—	A valid credential that may not do this.

200 body — 5 fields.

Field	In	Type	Always
`created`	body	integer	—
`data`	body	openai.ImageResponseDataInner[]	—
`data[].b64_json`	body	string	—
`data[].revised_prompt`	body	string	—
`data[].url`	body	string	—

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo images generations

.ts

.py

.go

.rs

.java

import { Configuration, AiApi } from 'hanzoai';

const api = new AiApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postImagesGenerations();

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AiApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AiApi(client).post_images_generations()

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.AiAPI.PostImagesGenerations(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, ai_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = ai_api::post_images_generations(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AiApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new AiApi(client).postImagesGenerations();

curl -X POST https://api.hanzo.ai/v1/images/generations \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP declares no tool for ai — tools/list on https://api.hanzo.ai/v1/mcp names the products it does reach. Use HTTP or an SDK.

AI API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousCreate embeddings NextCreate count tokens