DataEyesAI
Official SiteConsoleDocs Home
Getting StartedDeveloper ToolsAI Models APITerms & Policies
Official SiteConsoleDocs Home
Getting StartedDeveloper ToolsAI Models APITerms & Policies
  1. Getting Started
  • Documentation
    • Getting Started
      • Welcome to DataEyesAI
      • Quickstart
      • API Keys and Authentication
      • Base URL and SDKs
      • Models, Groups, and Pricing
    • Developer Tool Integration
      • Claude Code
      • Claude Code for VS Code
      • Codex
      • OpenClaw
      • OpenCode
      • Cline
      • Gemini CLI
      • Grok CLI
      • n8n
      • AutoClaw
      • Other tools
      • Claude Code 400 troubleshooting
    • AI Models API
      • API Overview
      • Chat Completions
      • Responses
      • Messages (Claude)
      • Gemini (generateContent)
      • Embeddings
      • Image Models
        • Images
        • Gemini Image Generation
        • Grok Imagine Image
      • Midjourney format
        • Midjourney API Reference
        • Task query interface
        • Upload image
        • Get seed (Seed)
        • Submit Imagine task
        • Query tasks based on ID list
        • FaceSwap
        • Execute Action operation
        • /mj/submit/blend
        • Submit Describe task
        • Submit Modal
        • Refresh link
        • Edit image
        • Query task status by task ID
        • Get the seed of the task image
      • Video Model
        • FLUX Video Generation (flux-3-video)
        • Grok Video Generation
          • 00-Overview
          • 01-Text-to-Video
          • 02-Image-to-Video
          • 03-Reference-to-Video
          • 04-Video-Editing
          • 05-Video-Extension
        • Seedance Video Generation
          • 00-Overview
          • 01-Create-Video-Generation-Task
          • 02-Query-Video-Generation-Task
          • 03-Query-Video-Generation-Task-List
          • 04-Cancel-or-Delete-Task
          • Seedance Private Asset Library API Documentation
        • MiniMax-H3 Video Generation
          • 00-Overview
          • 01-Create-Video-Generation
          • 02-Create-Video-Regeneration
          • 03-Create-H3-Context-IR
          • 04-Query-Task
          • 05-List-Tasks
          • 06-Cancel-or-Delete-Task
        • Hailuo Video Generation
          • 00-Overview
          • 01-Text-to-Video-T2V
          • 02-Image-to-Video-I2V
          • 03-First-Last-Frame-FL2V
          • 04-Subject-Reference-S2V
          • 05-Query-Task-Status
          • 06-Video-Download
          • 99-Appendix-Camera-Movement-and-Webhooks
        • Jimeng Video Generation
          • 00-Overview
          • 01-3.0-Pro-Video-Generation
          • 02-720P-Text-to-Video
          • 03-720P-Image-to-Video-First-Frame
          • 04-720P-Image-to-Video-Start-End-Frame
          • 05-720P-Image-to-Video-Camera
          • 06-1080P-Text-to-Video
          • 07-1080P-Image-to-Video-First-Frame
          • 08-1080P-Image-to-Video-Start-End-Frame
          • 09-Error-Codes
        • Kling AI Video Generation
          • 00-Overview
          • 01-Text-to-Video
          • 02-Image-to-Video
          • 03-Omni-Video
          • 04-Multi-Image-to-Video
          • 05-Motion-Control
          • 06-Multi-Elements
          • 07-Video-Extension
          • 08-Lip-Sync
          • 09-Avatar
          • 10-Text-to-Audio
          • 11-Video-to-Audio
          • 12-TTS
          • 13-Custom-Voices
          • 14-Image-Recognition
          • 15-Element-Management
          • 16-Video-Effects
          • 17-Kling-4.0-Video-Generation
        • Vidu Video Generation
          • 00-Overview
          • 01-Text-to-Video
          • 02-Image-to-Video
          • 03-Reference-to-Video
          • 04-Start-End-Frame
          • 05-Multi-Frame
          • 06-Scene-Template
          • 07-Template-Story
          • 08-Query-Tasks
        • HappyHorse
          • HappyHorse Text-to-Video
          • HappyHorse Image-to-Video (First Frame)
          • HappyHorse Reference-to-Video
          • HappyHorse Video Editing
        • Wan Video Generation
          • 00-Overview.md
          • 01-Text-to-Video
          • 02-Image-to-Video
          • 03-Reference-to-Video
          • 04-Video-Editing
          • 05-First-Last-Frame-to-Video
          • 06-Motion-Transfer-and-Character-Swap
          • 07-Digital-Human-Video
          • 08-VACE-Video-Editing
          • 09-Query-Task
      • Audio API
        • Audio API
        • Gemini TTS API
        • Google DeepMind Lyria API
        • Elevenlabs Speech to Text API Reference
    • Search / Reader Product
      • Search & Reader
      • Web Search
      • Search and Read
      • Video Search
      • Web Reader
      • Document Parsing
      • Trending
      • Weather
      • All City ID
    • Advanced & System API
      • FAQ
      • System interface
        • API Key & Quota Query API
        • API Key Management API
      • API Reference​​
        • Error Codes
        • Rate Limits and Billing Rules
      • List models
        • Models
  • Terms & Policies
    • DataEyesAI API Terms of Service
    • DataEyesAI Legal Notice and Privacy Policy
    • DataEyesAI Paid Services Agreement
    • Automatic Renewal Service Rules
  1. Getting Started

API Keys and Authentication

DataEyesAI uses two independent types of keys:
Key typeWhere to get itAPIs it can callBilling
Model API keyConsole → Model API keyAll model APIs: text, image, video, audio (https://studio.dataeyes.ai)Deducted from your model balance by usage
Search & Reader API keyConsole → MCP Products → Access & KeysSearch, reader, document parsing, and related APIs (https://openapi.dataeyes.ai)Deducted per call

Model API key#

Create a key#

When you sign up, 3 keys are created for you automatically, one for each group type, and are ready to use. To manage projects, team members, or environments separately, click "New" on the Model API key page.

Group type#

When you create a key, you choose a group type. It decides which channel group your requests are routed to:
Group typeBehaviorBest for
Stability FirstAutomatically picks the most available channel among your groupsProduction
Price FirstAutomatically picks the cheapest channel among your groupsCost-sensitive batch jobs
Specify groupAlways uses the group you chooseLocking in a price or channel
There are two kinds of groups:
default (Official price): all models, billed at official prices.
Brand groups (such as gemini, openai, claude-aws): discounted prices for that brand's models. See Group pricing on the model detail page for the exact discount.
Open any model in the Model Hub to see which groups it supports and the price in each. See Models, groups, and pricing.

Security settings#

When you create or edit a key, consider setting:
Quota limit: a USD spending cap for the key. The key stops working once the cap is reached, protecting you from runaway costs caused by bugs.
Expiration: useful for temporary tests or contractor projects.
IP whitelist: only allow calls from specific IPs (one per line, CIDR supported), so a leaked key cannot be abused.
Model limits: optional; restrict the key to specific models. Usually not needed.

Search & Reader API key#

Switch to "MCP Products" at the top of the console and open Access & Keys to see your base URL and API key.
WARNING
The full key is shown only once, when your account is created or when you rotate the key. Afterwards only the first and last characters are shown. Save it right away. If you lose it, click "Rotate" to generate a new key; the old key stops working immediately.

Pass the key in requests#

All APIs require HTTPS. Each protocol uses its standard header, and the gateway supports all of them:
ProtocolHeaderExample
OpenAI-compatible (including Search & Reader APIs)AuthorizationAuthorization: Bearer sk-xxx
Anthropic Messagesx-api-key or Authorizationx-api-key: sk-xxx
Gemini nativex-goog-api-keyx-goog-api-key: sk-xxx
TIP
When entering the key in an SDK or third-party tool, enter only the raw string starting with sk-. Do not add the Bearer prefix yourself; the SDK handles it.

Security best practices#

Never put keys in frontend code, mobile app packages, or public repositories. Read them from environment variables instead, for example export DATAEYES_API_KEY=sk-xxx.
Use a separate key per project so you can set limits, disable, and reconcile each one independently.
If you suspect a key has leaked, delete or disable it in the console immediately and create a replacement.

Next steps#

Base URL and SDKs: the correct base URL for each SDK and tool.
Models, groups, and pricing: how groups and pricing work.
Previous
Quickstart
Next
Base URL and SDKs