A unified LLM API gateway providing access to multiple AI models through standardized endpoints.

New API is a unified LLM API gateway that aggregates access to various AI providers through a single interface. It supports over 30 providers including OpenAI, Claude, Gemini, Grok, MoonshotAI, Zhipu, DeepSeek, and Qwen.

Key endpoints follow standardized patterns:

/v1/chat/completions, /v1/responses, /v1/messages for chat completions
/v1/embeddings for embeddings
/v1/rerank for reranking
/v1/images/generations, /v1/images/edits, /v1/images/variations for image generation and editing
/v1/audio/speech, /v1/audio/transcriptions, /v1/audio/translations for audio processing
/v1beta/models for model management

The service emphasizes competitive pricing and stability without subscription requirements. Users can integrate by replacing their model BASE URL with New API's endpoints.

Time	Model	Speed	Latency
Nov 25, 12:02 PM	deepseek-v3.1:671b	72.08 t/s	1.88s
Nov 25, 12:01 PM	gpt-oss-120b	306.96 t/s	1.64s
Nov 25, 12:00 PM	qwen-3-235b-a22b-instruct-2507	449.95 t/s	1.47s
Oct 31, 11:01 AM	llama-4-scout-17b-16e-instruct	334.77 t/s	0.84s
Oct 31, 11:00 AM	qwen-3-coder-480b	388.56 t/s	1.41s

New API

Supported Models

Recent Test Records

New API

About New API

Supported Models

Recent Test Records