ModelStream LogoModelStream Logo
Models
Video API
Image API
Chat API
Audio API
Studio
Pricing
Docs
Menu
IntroductionQuickstartAPI KeysUse with Hermes AgentUse with OpenClaw
Model ListBilling Guide
ModelStream

Video API

  • Seedance 2.0
  • Happyhorse 1.0
  • Vidu Q3
  • Kling V3.0
  • Veo 3.1
  • Wan 2.7
  • More Video Models →

Image API

  • GPT Image 2
  • Nano Banana 2
  • Seedream 5.0
  • Imagen 4
  • Qwen Image 2.0
  • Z-Image Turbo
  • More Image Models →

Audio API

  • Suno Music
  • Qwen3 TTS Flash
  • More Audio Models →

Chat API

  • GLM-5.2
  • Claude Opus 4.8
  • Gemini 3.5 Flash
  • Qwen 3.7 Max
  • GPT 5.5
  • More Chat Models →

About Us

  • Privacy Policy
  • Terms of Service
  • Support
  • Enterprise

© 2026 ModelStream Inc. All rights reserved.

API Documentation
API Reference
Images
Generate Image

Generate Image

Loading models...
G
GPT-3.5-Turbo (gpt-3.5-turbo-0125)
gpt-3.5-turbo-01250 models support this endpoint

GPT-3.5-Turbo is a time-tested, cost-effective classic LLM. It delivers high generation speed and stability while maintaining excellent comprehension capabilities. It is ideally suited for routine chat, simple text generation, format conversion, and lightweight applications with strict requirements on response latency.

Generate image

https://api.modelstream.ai
POST/v1/images/generations

Authentication

BearerAuth
AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

system_prompt?string

Global instructions or persona for the model.

Example Value: You are a helpful and expert assistant.Placeholder: e.g., You are a senior software architect...
prompt*string
RequiredExample Value: Hello! What can you do?Placeholder: Enter your question or instructions...
temperature?number

Higher values make output more random, lower more deterministic.

Example Value: 1Value Range: 0 ≤ value ≤ 2step: 0.1
top_p?number

Nucleus sampling threshold; an alternative to temperature.

Example Value: 1Value Range: 0 ≤ value ≤ 1step: 0.05
presence_penalty?number

Increases the tendency to talk about new topics.

Example Value: 0Value Range: -2 ≤ value ≤ 2step: 0.1
frequency_penalty?number

Reduces the likelihood of repeating the same text verbatim.

Example Value: 0Value Range: -2 ≤ value ≤ 2step: 0.1
seed?number

A fixed seed yields more reproducible results (optional).

Value Range: 0 ≤ value ≤ 2147483647
max_completion_tokens?number
Example Value: 8192Value Range: 1 ≤ value ≤ 128000
response_format?string
Example Value: text
Enum/Options:
Text: textJSON Object: json_object
stream?boolean
Example Value: true

Response Parameters

application/json
200apiDocs.responses.successGenerateImage
created?integer

Parameter description for Created

data?array

Parameter description for Data

curl -X POST "https://api.modelstream.ai/v1/images/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-3.5-turbo-0125",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software architect."
    },
    {
      "role": "user",
      "content": "Explain the trade-offs between microservices and a monolith."
    }
  ],
  "temperature": 0.7,
  "top_p": 1,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "max_completion_tokens": 4096,
  "stream": true
}'
{
  "created": 0,
  "data": [
    {
      "url": "string",
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ]
}