AI Coding Live News

Cloudflare AI Search goes GA: native multimodal embeddings + PDF OCR; billing from Nov 1; hybrid search default

On 2026-10-01 Cloudflare made AI Search generally available: managed index/retrieval (Workers AI + Vectorize + R2 + Browser Run) ships native multimodal embeddings (Qwen3-VL-Embedding), OCR for scanned PDFs, 10 MiB text/OCR PDF limits, hybrid search by default, and billing from 2026-11-01 with a free allotment.

Cloudflare AI Search goes GA: native multimodal embeddings + PDF OCR; billing from Nov 1; hybrid search default

Key Takeaways

  • GA 2026-10-01: changelog + blog.cloudflare.com/ai-search-ga/
  • Multimodal embeddings: @cf/qwen/qwen3-vl-embedding-2b and google-ai-studio/gemini-embedding-2; image queries via REST/public endpoint
  • OCR on all accounts; text/code + OCR PDFs up to 10 MiB (non-OCR PDFs stay 4 MiB)
  • Hybrid search default; Workers AI embed/rerank folded into AI Search pricing (not Workers AI bill)
  • Pricing: $0.75/1M ingest tokens, $2/GB-mo storage, $0.75/1k semantic, $0.10/1k full-text; free tier 5M ingest / 10 GB / 1k+1k queries; bill from Nov 1, 2026
Read full story
Linked Models & Agents:

Cloudflare enhances Workers AI with D1 integration, launching native edge runtime for fullstack AI coding agents

Cloudflare announced an edge-native runtime for AI agent builders. Integrating Workers AI with D1 relational storage and Vectorize vector indexes allows agent workflows to maintain session state, semantic recall, and model inference across 330+ global edge locations with sub-50ms latency.

Key Takeaways

  • Unifies Workers AI, D1 SQL, and Vectorize for edge-native agent architectures.
  • Global 330+ city edge points deliver sub-50ms roundtrip session persistence.
  • Shipped with starter templates and TypeScript SDK for rapid agent deployment.
Read full story
Linked Models & Agents: