Features
Experiment tracking with auto-logging
Model registry with lineage
Dataset versioning and artifact storage
Collaborative dashboards and reports
Weave LLM tracing and debugging
LLM evaluations with scorers
Production monitoring with guardrails
Serverless RL and SFT fine-tuning
Serverless inference for open-source models
CI/CD automations and alerts
CoreWeave Sandboxes for isolated runs
Multi-cloud support (AWS, GCP, Azure)
Local server deployment (Docker)
Real-time web search API for agents
Content extraction and cleaning
/research endpoint with state-of-the-art benchmarks
Dynamic filtering — model programs own search filters via Bash/Python
180 ms p50 median latency on /search
Intelligent caching and indexing
300M+ monthly request capacity
Built-in PII, prompt injection, and malicious source filters
Drop-in integration with OpenAI, Anthropic, Groq
x402: pay-per-query with USDC wallet on Base
Integration with Arcade.dev, LangChain, MCP Marketplace
Structured, chunked output for LLM ingestion
Developer-friendly API with comprehensive docs