
Hindsight Models and Inference API精选
Small, fast models for reranking, embeddings and decisions
Hosted models for the steps around your LLM: reranking, embeddings and typed decisions. Point your Cohere or OpenAI client at inference.hindsight.vectorize.io and keep your code. hs-rerank-1 and hs-embed-1 are the most accurate small open models on our benchmarks and run fast on a CPU; hs-decide-1-flash answers yes/no, pick-one and how-likely questions in 167 ms, instead of an LLM call. From $0.005 per 1M tokens, $5 free credit, open weights on Hugging Face.
2026-11-04 同榜
801
Wanaka StudioMake and publish 3D games with the first AI game engine▲ 43202
Floot PaymentsTake payments in apps you build in ChatGPT and Claude▲ 31903
PreluluBe the main character: chat & video roleplay any story▲ 26504
Render SandboxesA computer for every agent▲ 23605
OpenMailGive your AI agents an identity through email▲ 19906
Orphex MCPRun your entire digital marketing stack via one unified MCP▲ 17007
OpusClip 4.0Turn raw footage into ready-to-publish videos with AI▲ 14608
fileForensicsReal or not? Check files before your AI trusts them.▲ 126