📡 API Endpoints
🤖 Claude Code & MCP Clients
Use these routes when setting ANTHROPIC_BASE_URL. Claude Code hits /v1/messages directly.
POST
https://airouter.task4you.cz/v1/messages
Claude Code compatible shortcut
GET
https://airouter.task4you.cz/v1/models
Model list for Claude Code
🔶 Anthropic Native Format
Full Anthropic API format — for Cursor, Continue.dev (anthropic provider), custom scripts using the Anthropic SDK.
POST
https://airouter.task4you.cz/api/v1/anthropic/messages
Anthropic Messages API
GET
https://airouter.task4you.cz/api/v1/anthropic/models
🟢 OpenAI-Compatible Format (GLM backend)
OpenAI format translated to GLM/Anthropic backend — for LibreChat, Open WebUI, Continue.dev (openai provider), n8n, LangChain.
Supports Vision Mode: add -vision suffix to any model name.
POST
https://airouter.task4you.cz/api/v1/openai/chat/completions
Supports streaming, tools, vision, file uploads, thinking mode (-t suffix)
GET
https://airouter.task4you.cz/api/v1/openai/models
GET
https://airouter.task4you.cz/api/v1/openai/models/{model_id}
⚪ OpenAI Native (GPT Models)
Pass-through to Z.ai coding endpoint — for GPT-4o, o1, o1-mini. No format conversion.
POST
https://airouter.task4you.cz/api/v1/openai-native/chat/completions
Models: gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo, o1, o1-mini, o1-preview
GET
https://airouter.task4you.cz/api/v1/openai-native/models
🛠 Utility
GET
https://airouter.task4you.cz/api/v1/health
Health check
POST
https://airouter.task4you.cz/api/v1/upload/vision
File upload for Vision Mode
GET
https://airouter.task4you.cz/files/{filename}
Serve uploaded files (TTL-controlled)
⚡ Quick Examples
Claude Code — ~/.claude/settings.json
{
"env": {
"ANTHROPIC_BASE_URL": "https://airouter.task4you.cz",
"ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
"ANTHROPIC_MODEL": "claude-sonnet-4-5",
"ANTHROPIC_SMALL_FAST_MODEL": "claude-haiku-4-5",
"API_TIMEOUT_MS": "600000",
"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"
}
}
Anthropic Native — cURL
curl -X POST https://airouter.task4you.cz/api/v1/anthropic/messages \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-4.7",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Hello!"}]
}'
OpenAI-Compatible — cURL (with thinking mode)
curl -X POST https://airouter.task4you.cz/api/v1/openai/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-4.7-t",
"stream": true,
"messages": [{"role": "user", "content": "Solve this step by step..."}]
}'
Continue.dev — config.json
{
"models": [
{
"title": "GLM-4.7 via task4you",
"provider": "anthropic",
"model": "glm-4.7",
"apiBase": "https://airouter.task4you.cz/api/v1/anthropic",
"apiKey": "YOUR_API_KEY"
}
]
}
LibreChat — librechat.yaml
endpoints:
custom:
- name: "task4you AI Router"
baseURL: "https://airouter.task4you.cz/api/v1/openai"
apiKey: "YOUR_API_KEY"
models:
default: ["glm-4.7", "glm-4.6", "glm-4.5"]
fetch: true