HU
Hugging Face
Inference
The model hub and open-source commons for AI, with serving via Inference Endpoints and Inference Providers.
inference models open-source
Category
Inference
Model-serving infrastructure and inference providers.
8 tools tracked 1 editor's picks
Ollama
Inference
The simplest way to run open models locally: one command, OpenAI-compatible API, now with a hosted cloud option.
inference local-llm open-weights
Fireworks AI
Inference
High-performance serverless inference for OSS LLMs, fine-tuning, fast endpoints, fast time-to-production.
inference llm oss
Groq
Inference
Custom LPU silicon for LLM inference, speed records on Llama, Qwen, and Whisper at predictable per-token pricing.
inference llm lpu
Modal
Inference
Serverless GPU + CPU for Python, pay per second, deploy custom inference, run anything.
inference gpu serverless
OpenRouter
Inference
One API across 400+ models from 60+ providers, Anthropic, OpenAI, OSS, all behind a unified endpoint.
inference router multi-provider
Replicate
Inference
Run any open-source model with a single API, per-second GPU billing across LLM, image, video, voice.
inference multimodal image
Together AI
Inference
Serverless inference for 200+ open-source models, fast, cheap, and the workhorse for OSS LLMs.
inference llm oss