Tag
Every item tagged api, newest first.
GLM 5.2 API is live, weights are on HuggingFace under MIT, and Ollama already has it. You can now run it locally or call it through your existing gateway.
Hugging Face now offers speech-to-speech translation capabilities via an API endpoint. This feature allows developers to integrate speech-to-speech functionality into their applications. The API supports various languages and models. You can access the API documentation for more information.
Hugging Face has launched the Messages API, enabling developers to build applications on open LLMs like Llama-3 and Mistral-7B. The API provides a unified interface for text and chat-based interactions, supporting multiple models. This move aims to reduce dependence on proprietary LLM APIs and promote open LLM adoption.
Hugging Face launched Inference for PROs, a paid API service for high-priority access to optimized model inference. The service targets professional developers and enterprises requiring low-latency, high-throughput model serving. Pricing starts at $0.0015 per minute of inference time. You can use it to deploy and serve models at scale.