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
Getting Started
Quickstart

Quickstart

Integrate and make your first request in minutes through four simple steps.

Step 1: Sign up and Log in

Get Platform Access

Visit the platform and log in using Email+Password or a Web3 wallet. Once logged in, you can view your account status and balance in the top right corner.

Step 2: Recharge or Redeem Credits

Acquire Usage Credits

The platform uses a Quota-based billing model. You can go to the "Wallet/Recharge" page for online payments, or use a redeem code to get credits.

Step 3: Create API Key

Generate and Configure your Token

Go to the "Tokens" page and click "New". It is recommended to set a descriptive name for the key and configure quota caps or IP whitelists. Please securely save the generated sk-... key.

Step 4: Make Your First Call

Integrate Core Features

Call using native libraries.

cURL
curl https://api.modelstream.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Introduce yourself"}
    ]
  }'
Python
from openai import OpenAI
 
 client = OpenAI(
     base_url="https://api.modelstream.ai/v1",
     api_key="sk-xxxxxxxx",
 )
 
 resp = client.chat.completions.create(
     model="gpt-4o-mini",
     messages=[{"role": "user", "content": "Introduce yourself"}],
 )
 print(resp.choices[0].message.content)
Node.js
import OpenAI from "openai";
 
 const client = new OpenAI({
   baseURL: "https://api.modelstream.ai/v1",
   apiKey: "sk-xxxxxxxx",
 });
 
 const resp = await client.chat.completions.create({
   model: "gpt-4o-mini",
   messages: [{ role: "user", "content": "Introduce yourself" }],
 });
 
 console.log(resp.choices[0].message.content);

Native Protocol Passthrough

Base URL

Please use the unified gateway: https://api.modelstream.ai

Native Protocol Passthrough

Fully supports Claude native protocols (Headers: x-api-key, anthropic-version) and Gemini native protocols (Header: x-goog-api-key).

What's Next?

You have successfully integrated! Next, you can read "API Keys" to learn security best practices, or check the "Model List" to explore all the multimodal models we support.

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.