Images

Generate images using the OpenAI-compatible chat completions format with modalities.

Endpoint

POST https://api.scalellm.dev/v1/chat/completions

Examples

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

response = client.chat.completions.create(
    model="gemini-3-pro-image-preview",
    messages=[
        {"role": "user", "content": "Generate an image of a cat"}
    ],
    extra_body={"modalities": ["image", "text"]}
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const response = await client.chat.completions.create({
  model: 'gemini-3-pro-image-preview',
  messages: [
    { role: 'user', content: 'Generate an image of a cat' }
  ],
  modalities: ['image', 'text']
});

console.log(response.choices[0].message.content);

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "messages": [
      {"role": "user", "content": "Generate an image of a cat"}
    ],
    "modalities": ["image", "text"]
  }'

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (`gemini-3-pro-image-preview`)
`messages`	array	Yes	Array of message objects
`modalities`	array	Yes	Must include `["image", "text"]` for image generation
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	float	No	Randomness (0-2, default 1)

Message Object

Field	Type	Description
`role`	string	`system`, `user`, or `assistant`
`content`	string	Message content (image prompt)

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699000000,
  "model": "gemini-3-pro-image-preview",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": [
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,iVBORw0KGgo..."
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 0,
    "total_tokens": 10
  }
}

More Examples

Artistic Image

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

response = client.chat.completions.create(
    model="gemini-3-pro-image-preview",
    messages=[
        {"role": "user", "content": "An oil painting of a serene mountain landscape at dawn"}
    ],
    extra_body={"modalities": ["image", "text"]}
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const response = await client.chat.completions.create({
  model: 'gemini-3-pro-image-preview',
  messages: [
    { role: 'user', content: 'An oil painting of a serene mountain landscape at dawn' }
  ],
  modalities: ['image', 'text']
});

console.log(response.choices[0].message.content);

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "messages": [
      {"role": "user", "content": "An oil painting of a serene mountain landscape at dawn"}
    ],
    "modalities": ["image", "text"]
  }'

Product Visualization

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

response = client.chat.completions.create(
    model="gemini-3-pro-image-preview",
    messages=[
        {"role": "user", "content": "A sleek smartphone on a minimalist white desk, product photography"}
    ],
    extra_body={"modalities": ["image", "text"]}
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const response = await client.chat.completions.create({
  model: 'gemini-3-pro-image-preview',
  messages: [
    { role: 'user', content: 'A sleek smartphone on a minimalist white desk, product photography' }
  ],
  modalities: ['image', 'text']
});

console.log(response.choices[0].message.content);

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "messages": [
      {"role": "user", "content": "A sleek smartphone on a minimalist white desk, product photography"}
    ],
    "modalities": ["image", "text"]
  }'

Available Models

Model	Description
`gemini-3-pro-image-preview`	Multimodal with native image generation

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer sk_your_key`
`Content-Type`	Yes	`application/json`

For Gemini native format, see the Gemini Images endpoint.

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

Images

Images

Endpoint

Examples

Request Body

Message Object

Response

More Examples

Artistic Image

Product Visualization

Available Models

Headers

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

​Images

​Endpoint

​Examples

​Request Body

​Message Object

​Response

​More Examples

​Artistic Image

​Product Visualization

​Available Models

​Headers

Images

Endpoint

Examples

Request Body

Message Object

Response

More Examples

Artistic Image

Product Visualization

Available Models

Headers