Images

Générer des images (API compatible OpenAI)

Generate an image based on input parameters using an OpenAI compatible endpoint. This endpoint does not support the full feature set of the Venice Image Generation endpoint, but is compatible with the existing OpenAI endpoint.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST

images

generations

/api/v1/image/generations

curl --request POST \
  --url https://api.venice.ai/api/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A beautiful sunset over mountain ranges",
  "background": "auto",
  "model": "grok-imagine-image",
  "moderation": "auto",
  "n": 1,
  "output_compression": 100,
  "output_format": "png",
  "quality": "auto",
  "response_format": "b64_json",
  "size": "1024x1024",
  "style": "natural",
  "user": "user123",
  "anon_user_id": "end-user-123"
}
'

import requests

url = "https://api.venice.ai/api/v1/images/generations"

payload = {
    "prompt": "A beautiful sunset over mountain ranges",
    "background": "auto",
    "model": "grok-imagine-image",
    "moderation": "auto",
    "n": 1,
    "output_compression": 100,
    "output_format": "png",
    "quality": "auto",
    "response_format": "b64_json",
    "size": "1024x1024",
    "style": "natural",
    "user": "user123",
    "anon_user_id": "end-user-123"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'A beautiful sunset over mountain ranges',
    background: 'auto',
    model: 'grok-imagine-image',
    moderation: 'auto',
    n: 1,
    output_compression: 100,
    output_format: 'png',
    quality: 'auto',
    response_format: 'b64_json',
    size: '1024x1024',
    style: 'natural',
    user: 'user123',
    anon_user_id: 'end-user-123'
  })
};

fetch('https://api.venice.ai/api/v1/images/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/images/generations",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => 'A beautiful sunset over mountain ranges',
    'background' => 'auto',
    'model' => 'grok-imagine-image',
    'moderation' => 'auto',
    'n' => 1,
    'output_compression' => 100,
    'output_format' => 'png',
    'quality' => 'auto',
    'response_format' => 'b64_json',
    'size' => '1024x1024',
    'style' => 'natural',
    'user' => 'user123',
    'anon_user_id' => 'end-user-123'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.venice.ai/api/v1/images/generations"

	payload := strings.NewReader("{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/images/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}"

response = http.request(request)
puts response.read_body

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ]
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

Autorisations

Authorization

string

header

requis

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

En-têtes

Accept-Encoding

string

Supported compression encodings (gzip, br).

Exemple:

"gzip, br"

Corps

application/json

prompt

string

requis

A text description of the desired image.

Required string length: 1 - 1500

Exemple:

"A beautiful sunset over mountain ranges"

background

enum<string> | null

défaut:auto

This parameter is not used in Venice image generation but is supported for compatibility with OpenAI API

Options disponibles:

transparent,

opaque,

auto

Exemple:

"auto"

model

string

défaut:default

The model to use for image generation. Defaults to Venice's default image model. If a non-existent model is specified (ie an OpenAI model name), it will default to Venice's default image model.

Exemple:

"grok-imagine-image"

moderation

enum<string> | null

défaut:auto

auto enables safe venice mode which will blur out adult content. low disables safe venice mode.

Options disponibles:

low,

auto

Exemple:

"auto"

integer | null

défaut:1

Number of images to generate. Venice presently only supports 1 image per request.

Plage requise: 1 <= x <= 1

Exemple:

1

output_compression

integer | null

défaut:100

This parameter is not used in Venice image generation but is supported for compatibility with OpenAI API

Plage requise: 0 <= x <= 100

output_format

enum<string>

défaut:png

Output format for generated images

Options disponibles:

jpeg,

png,

webp

Exemple:

"png"

quality

enum<string> | null

défaut:auto

This parameter is not used in Venice image generation but is supported for compatibility with OpenAI API

Options disponibles:

auto,

high,

medium,

low,

hd,

standard

Exemple:

"auto"

response_format

enum<string> | null

défaut:b64_json

Response format. URL will be a data URL.

Options disponibles:

b64_json,

url

Exemple:

"b64_json"

size

enum<string> | null

défaut:auto

Size of generated images. Default is 1024x1024

Options disponibles:

auto,

256x256,

512x512,

1024x1024,

1536x1024,

1024x1536,

1792x1024,

1024x1792

Exemple:

"1024x1024"

style

enum<string> | null

défaut:natural

This parameter is not used in Venice image generation but is supported for compatibility with OpenAI API

Options disponibles:

vivid,

natural

Exemple:

"natural"

user

string

This parameter is discarded and is supported for compatibility with OpenAI API. It is not an alias of anon_user_id.

Exemple:

"user123"

anon_user_id

string

Optional identifier for the API customer's end user. Combined with the Venice user id when attributing the request to upstream providers. Distinct from the discarded OpenAI user field. Must be printable ASCII and must not contain ||.

Required string length: 1 - 128

Pattern: ^[\x20-\x7E]+$

Exemple:

"end-user-123"

Réponse

Successfully generated image

created

integer

requis

Unix timestamp for when the request was created

Exemple:

1713833628

data

object[]

requis

Option 1
Option 2

Show child attributes

⌘I

/api/v1/image/generations

curl --request POST \
  --url https://api.venice.ai/api/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A beautiful sunset over mountain ranges",
  "background": "auto",
  "model": "grok-imagine-image",
  "moderation": "auto",
  "n": 1,
  "output_compression": 100,
  "output_format": "png",
  "quality": "auto",
  "response_format": "b64_json",
  "size": "1024x1024",
  "style": "natural",
  "user": "user123",
  "anon_user_id": "end-user-123"
}
'

import requests

url = "https://api.venice.ai/api/v1/images/generations"

payload = {
    "prompt": "A beautiful sunset over mountain ranges",
    "background": "auto",
    "model": "grok-imagine-image",
    "moderation": "auto",
    "n": 1,
    "output_compression": 100,
    "output_format": "png",
    "quality": "auto",
    "response_format": "b64_json",
    "size": "1024x1024",
    "style": "natural",
    "user": "user123",
    "anon_user_id": "end-user-123"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'A beautiful sunset over mountain ranges',
    background: 'auto',
    model: 'grok-imagine-image',
    moderation: 'auto',
    n: 1,
    output_compression: 100,
    output_format: 'png',
    quality: 'auto',
    response_format: 'b64_json',
    size: '1024x1024',
    style: 'natural',
    user: 'user123',
    anon_user_id: 'end-user-123'
  })
};

fetch('https://api.venice.ai/api/v1/images/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.venice.ai/api/v1/images/generations",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => 'A beautiful sunset over mountain ranges',
    'background' => 'auto',
    'model' => 'grok-imagine-image',
    'moderation' => 'auto',
    'n' => 1,
    'output_compression' => 100,
    'output_format' => 'png',
    'quality' => 'auto',
    'response_format' => 'b64_json',
    'size' => '1024x1024',
    'style' => 'natural',
    'user' => 'user123',
    'anon_user_id' => 'end-user-123'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.venice.ai/api/v1/images/generations"

	payload := strings.NewReader("{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.venice.ai/api/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/images/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"A beautiful sunset over mountain ranges\",\n  \"background\": \"auto\",\n  \"model\": \"grok-imagine-image\",\n  \"moderation\": \"auto\",\n  \"n\": 1,\n  \"output_compression\": 100,\n  \"output_format\": \"png\",\n  \"quality\": \"auto\",\n  \"response_format\": \"b64_json\",\n  \"size\": \"1024x1024\",\n  \"style\": \"natural\",\n  \"user\": \"user123\",\n  \"anon_user_id\": \"end-user-123\"\n}"

response = http.request(request)
puts response.read_body

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ]
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}