New API is a unified LLM API gateway that aggregates access to various AI providers through a single interface. It offers standardized endpoints compatible with OpenAI's API format, allowing developers to switch between models by changing the base URL.
Key capabilities:
- Chat completions via
/v1/chat/completions,/v1/responses,/v1/responses/compact, and/v1/messages - Model management through
/v1beta/models - Embeddings via
/v1/embeddings - Reranking with
/v1/rerank - Image generation, editing, and variations via
/v1/images/generations,/v1/images/edits, and/v1/images/variations - Audio processing including speech synthesis (
/v1/audio/speech), transcription (/v1/audio/transcriptions), and translation (/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: Competitive pricing, stable service, and no subscription requirements. The platform emphasizes ease of integration by maintaining API compatibility with existing workflows.
Typical use cases: Developers and businesses seeking to leverage multiple LLMs without managing separate API integrations, applications requiring multimodal AI capabilities (text, image, audio), and projects needing cost-effective access to various AI models.
