Docs: LLM API Quickstart & Integration Guides
Overview
Introduction
Quickstart
FAQ
Models
Models & naming
Chinese models
Features
Streaming
Tool calling
Structured outputs
Image inputs
Image generation
Prompt caching
Reasoning models
Routing & failover
Auto router
Billing
Pricing modes
Balance & top-ups
Usage lookup
API reference
API overview
Authentication
Chat Completions
Responses
Messages (Anthropic)
Gemini native API
Models
Embeddings
Errors
Limits & quotas
Integrations
OpenAI SDK
Anthropic SDK
Claude Code
Codex CLI
Gemini CLI
Chat clients
Privacy & data
Data & logging