Baseten
Baseten
Production inference platform with dedicated deployments.
- Version
- 2025
- Cost
- Usage-based, enterprise tiers
- Model
- open weights
Infrastructure & Serving
Model registries, inference platforms, vector stores and the eval/observability layer everything else is built on.
17 tools · 0 changes / 30d
Braintrust
Braintrust
Eval-first platform for shipping LLM features safely.
- Version
- 2025
- Cost
- Free tier, usage-based
- Model
- model-agnostic
Chroma
Chroma
Embedded-first vector store popular in prototypes and agents.
- Version
- 1.x
- Cost
- Open source; cloud usage-based
- Model
- embeddings-agnostic
Fireworks AI
Fireworks AI
Low-latency serving for open models and custom fine-tunes.
- Version
- 2025
- Cost
- Per-token usage
- Model
- Llama
Hugging Face
Hugging Face
The model and dataset registry the open ecosystem runs on.
- Version
- Hub
- Cost
- Free, $9/mo Pro, enterprise from $20/user
- Model
- hosts most open weights
LangSmith
LangChain
Tracing, evals and monitoring for LLM applications.
- Version
- 2025
- Cost
- Free dev tier, $39/user/mo Plus
- Model
- model-agnostic
LM Studio
LM Studio
Desktop app for running and serving local models.
- Version
- 0.3x
- Cost
- Free for personal use
- Model
- open weights
Modal
Modal Labs
Serverless GPU compute for Python-native AI workloads.
- Version
- 2025
- Cost
- Per-second GPU billing, $30 free
- Model
- bring your own
Ollama
Ollama
Local model runner that made desktop inference trivial.
- Version
- 0.x
- Cost
- Free
- Model
- Llama
OpenRouter
OpenRouter
One API in front of 400+ models with live price and latency data.
- Version
- 2025
- Cost
- Pass-through pricing + 5%
- Model
- 400+ models
Pinecone
Pinecone
Managed vector database built for retrieval at scale.
- Version
- 2025
- Cost
- Free tier, usage-based serverless
- Model
- embeddings-agnostic
Replicate
Replicate
Run and ship any open model behind a simple API.
- Version
- 2025
- Cost
- Per-second GPU billing
- Model
- FLUX
Scale AI
Scale AI
Data engine and evaluation for frontier model builders.
- Version
- 2025
- Cost
- Enterprise quoted
- Model
- serves frontier labs
Together AI
Together AI
Open-model inference and fine-tuning at frontier speed.
- Version
- 2025
- Cost
- Per-token, from $0.06/M
- Model
- Llama
vLLM
vLLM (PyTorch Foundation)
The de facto open-source inference engine for LLM serving.
- Version
- 0.1x
- Cost
- Open source
- Model
- serves any open weights
Weaviate
Weaviate
Open-source vector database with built-in hybrid search.
- Version
- 1.3x
- Cost
- Open source; cloud from $25/mo
- Model
- embeddings-agnostic
Weights & Biases
CoreWeave
Experiment tracking and Weave evals for AI teams.
- Version
- 2025
- Cost
- Free personal, from $50/user/mo
- Model
- framework-agnostic
Recent changes in Infrastructure & Serving
No changes recorded yet.