LogoLogo

Quick Start

Complete your first API call in 5 minutes, and learn about the V1 API, Skills, and MCP integration options

The Guid AI gateway exposes three primary integration options:

OptionBest forDocs
V1 Open APIBackend, mobile, and third-party SDK integrationCommon Conventions
SkillsAgents such as Claude, Cursor, Codex, OpenClaw, Hermes, and NemoClawSkills
MCP ServiceClients that connect via the MCP protocolConnection & Configuration

This guide helps you complete your first API call in about 5 minutes. Replace sk-xxx in the examples with your API Key.

1. Get an API Key

Create an API Key (token) in the Guid AI admin console. The format is typically sk-xxxxxxxx.

If you need to restrict models or configure an IP allowlist, finish those token settings before using the key in your integration.

2. List available models

curl https://www.guid.ai/v1/models \
  -H "Authorization: Bearer sk-xxx"

A successful response returns success: true and a data[] model list. Note the data[].id you want to use, and check supported_endpoint_types to confirm the capabilities that model supports.

See Models API.

3. Choose your first endpoint by scenario

Text chat (most common)

curl https://www.guid.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See Text API.

Text-to-image

curl https://www.guid.ai/v1/images/generations \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A cat on a windowsill",
    "size": "1024x1024",
    "response_format": "url"
  }'

See Images API.

Video generation (async)

# 1. Create a task
curl https://www.guid.ai/v1/videos \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "A cat walking on the beach at sunset",
    "size": "1280x720",
    "seconds": 8
  }'

# 2. Poll status (replace task_xxx with the id returned above)
curl https://www.guid.ai/v1/videos/task_xxx \
  -H "Authorization: Bearer sk-xxx"

# 3. Download when complete
curl -L https://www.guid.ai/v1/videos/task_xxx/content \
  -H "Authorization: Bearer sk-xxx" \
  -o output.mp4

See Videos API.

Text-to-speech

# 1. List voices
curl https://www.guid.ai/v1/audio/voice/tts-1 \
  -H "Authorization: Bearer sk-xxx"

# 2. Synthesize speech
curl https://www.guid.ai/v1/audio/speech \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello world",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  -o speech.mp3

See Audio API.

4. Use Skills in an Agent (optional)

If you use Agent platforms such as Claude, Cursor, Codex, OpenClaw, Hermes, or NemoClaw:

  1. Download and extract guid-ai-skills.zip into the Agent's Skills directory
  2. Configure guid-ai-skills/.env:
GUIDAI_BASE_URL=https://www.guid.ai
GUIDAI_API_KEY=sk-xxx
  1. Describe your generation needs directly in the conversation

See Skills.

5. Documentation map

Getting started

V1 Open API (12 endpoints)

MCP Service

Skills

6. Next steps

GoalRead
Decide between REST / SkillsChoosing an Integration
Look up full endpoint parametersAPI capability docs
Call multimodal generation from an AgentSkills
Understand errors and billingCommon Conventions · Error Responses

Quick conventions: Base URL https://www.guid.ai · Auth Authorization: Bearer sk-xxx · Public API /v1/* · MCP /mcp

Choosing an Integration

Choose V1 Open API, Skills, or MCP based on your use case