EmbeddingGemma 2 on Workers AI
EmbeddingGemma 2 is available on Workers AI at $0.0017 per million input tokens.
The Deploy Log | Products | Free, no signup
15 updates to Cloudflare Workers from Cloudflare in The Deploy Log: each row Cloudflare published whose subject opens with Cloudflare Workers or Workers or names a feature in it, or names Workers anywhere in it. By publisher's dates alone: from to , a new one every 4 days on the median, the longest wait was 17 days, and 4 updates in the last 30 days. The newest is EmbeddingGemma 2 on Workers AI. 2 rows with no publisher's date, each listed by its edition's date. Each links the publisher's own page.
| Update | Date | Days after the one before |
|---|---|---|
| EmbeddingGemma 2 on Workers AI | 0 | |
| Inkling 2 Small on Workers AI | 3 | |
| Codex agent loop on Cloudflare Workers | 17 | |
| Workers Builds packageManager | 4 | |
| DeepSeek V4.1 Flash 1017 on Workers AI | 4 | |
| Pipecat PhoneLLM Mini on Workers AI | 3 | |
| Workers Builds preview URLs | 3 | |
| Clef-omni on Workers AI | 0 | |
| Cloudflare Workers flamegraphs | ||
| Workers KV Instant | edition's date | |
| Workers post-quantum crypto | edition's date | |
| Workers KV namespace jurisdictions | 0 | |
| Workers Observability in Custom Dashboards | 1 | |
| Workers Web Crypto ML-KEM/ML-DSA | 10 | |
| Python Workers |
EmbeddingGemma 2 is available on Workers AI at $0.0017 per million input tokens.
Inkling 2 Small is available on Workers AI with 1,048,576 token context and 20 requests per minute default rate limit.
An experimental Agents SDK example runs the Codex agent loop in a Cloudflare Durable Object with persistence and recovery.
Workers Builds now installs the npm version set in packageManager before dependencies, supporting npm, Yarn, pnpm, and Bun.
DeepSeek V4.1 Flash 1017 is available on Workers AI with a 1,048,576 token context window and 20 requests per minute default rate limit.
Pipecat PhoneLLM Mini is now available on Workers AI, built for voice agents and realtime AI applications.
Workers Builds now posts preview URLs to GitHub pull requests and GitLab merge requests within seconds of a build completing.
Clef-omni adds audio and video input, Clef-flash is cheaper, and Clef is faster.
On-demand CPU and memory profiling with flamegraphs for Workers and Durable Objects.
Workers KV Instant, powered by Quicksilver, offers 100 times faster p99 reads than classic mode with reads resolving in under two milliseconds at p99, and writes replicating in around 250ms for 99% of writes.
Cloudflare Workers added support for post-quantum-resistant algorithms within Web Crypto, including ML-KEM-768 and ML-KEM-1024 for key encapsulation and ML-DSA-44, ML-DSA-65, and ML-DSA-87 for signatures, behind the webcrypto_modern_algorithms compatibility flag.
Workers KV namespace jurisdictions are generally available with eu, us, and fedramp regions.
Cloudflare adds Workers Observability Logs and Traces datasets to Custom Dashboards, with up to 100 dashboards per account.
Workers Web Crypto API now supports ML-KEM-768, ML-KEM-1024, ML-DSA-44, ML-DSA-65, and ML-DSA-87.
Python Workers are now generally available on Cloudflare.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.