A unified LLM API gateway providing access to multiple AI models through standardized endpoints.
天絮 API is a unified gateway for accessing various large language models (LLMs) and AI services. It offers standardized API endpoints compatible with multiple providers, allowing users to switch between different models by changing the base URL.
Key capabilities:
- Chat completions (
/v1/chat/completions,/v1/responses,/v1/messages) - Model management (
/v1beta/models) - Embeddings (
/v1/embeddings) - Reranking (
/v1/rerank) - Image generation and editing (
/v1/images/generations,/v1/images/edits,/v1/images/variations) - Audio processing (
/v1/audio/speech,/v1/audio/transcriptions,/v1/audio/translations)
Supported providers include: MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, Xinference, and others.
Notable features: No subscription required, pay-as-you-go pricing model. The service emphasizes better pricing and stability compared to direct provider access.
Typical use cases: Developers and businesses needing unified access to multiple AI models without managing separate API integrations.

