Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt

Use this file to discover all available pages before exploring further.

Anyfast is fully compatible with the OpenAI Chat Completions API. If you’re already using the OpenAI SDK, switching to Anyfast requires only a base URL change — no code rewrite needed.

Endpoint

POST https://www.anyfast.ai/v1/chat/completions

Authentication

Include your Anyfast API key as a Bearer token:
Authorization: Bearer YOUR_API_KEY

Quick example

curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Supported models

ProviderModels
Anthropicclaude-opus-4-7-thinking, claude-opus-4-7, claude-sonnet-4-6, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-opus-4-6, claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-haiku-4-5-20251001, claude-3-7-sonnet-20250219, claude-3-5-sonnet-20241022
OpenAIgpt-5-4, gpt-5-3-codex, gpt-5-2, gpt-5-1, gpt-5, gpt-5-pro, gpt-5-mini, gpt-5-nano, gpt-4o, gpt-4o-mini, gpt-4-1, gpt-4
DeepSeekdeepseek-v3-2-speciale, deepseek-v3-2, deepseek-v3-1-terminus, deepseek-v3-1, deepseek-v3
Alibabaqwen3.5-397b-a17b, qwen3-coder-next, qwen3-coder, qwen3-235b-a22b, qwen3-32b, qwen3-14b, qwen2.5-72b-instruct
ByteDancedoubao-seed-2.0-pro, doubao-seed-2.0-code, doubao-seed-2.0-lite, doubao-seed-2.0-mini, doubao-seed-1-8-251228, doubao-seed-1-6-flash-250828, doubao-seed-1-6-251015, doubao-seed-1-6-lite-251015, doubao-seed-1-6-vision-250815
Zhipuglm-5.1-cache, glm-5.1, glm-4.7, glm-4.5, glm-5
MiniMaxminimax-m2.5, minimax-m2.1
MoonShotkimi-k2.5
xAIgrok-3, grok-3-mini, grok-4-fast-reasoning, grok-4-fast-non-reasoning, grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning
Googlegemini-3.1-pro-preview, gemini-3-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash

Features

  • Streaming — Set stream: true for real-time token streaming via SSE
  • Function calling — Use the tools and tool_choice parameters
  • JSON mode — Set response_format: { type: "json_object" }
  • Multi-turn conversations — Include full message history in messages