AI Infrastructure Services

by Groq · inference

An inference provider running open models on custom LPU hardware for extremely fast token generation.

by Langfuse · observability

An open-source LLM observability platform for tracing, evaluation, and prompt management.

by Modal · hosting

A serverless cloud platform for running AI workloads, with GPUs provisioned from Python code.

by OpenRouter · api-gateway

A unified API gateway that routes requests to hundreds of LLMs from a single endpoint.

by Ollama · inference

A tool for running open-source LLMs locally, with an OpenAI-compatible API and an optional cloud inference tier.

by Fireworks AI · inference

A fast inference platform for open models, optimized for low-latency production workloads.

by LangChain · observability

An observability and evaluation platform for LLM applications, from the makers of LangChain.

by Pinecone · vector-db

A fully managed vector database for semantic search and retrieval-augmented generation at scale.

by Replicate · hosting

A platform for running open-source models via API, with one-click deployment of custom models.

by Together AI · inference

An inference and fine-tuning platform for open-source models with competitive pricing.

by Weaviate · vector-db

An open-source vector database with hybrid search, self-hosting, and a managed cloud option.