Cloudflare Workers AI adds GLM 5.2

// 2h agoMODEL RELEASE

Cloudflare Workers AI adds GLM 5.2

Cloudflare has launched support for the new open-source GLM 5.2 model on its Workers AI serverless inference platform. Through a launch partnership and cooperation with the SGLang project, developers can now deploy and query GLM 5.2 at the edge on Cloudflare's network on day zero.

// ANALYSIS

Day-zero support for open-source releases shows Cloudflare's ambition to be the default runtime for open-weight AI models.

–Seamless SGLang integration ensures high-performance inference from day one.
–Helps Cloudflare compete with dedicated AI model hosts by offering edge compute capabilities combined with model hosting.
–Reinforces Cloudflare's commitment to supporting the rapidly evolving open-source AI ecosystem.

// TAGS

cloudflareworkers-aiglm-5.2sglangopen-sourceai-inference

DISCOVERED

2h ago

2026-06-16

PUBLISHED

3h ago

2026-06-16

RELEVANCE

7/ 10

AUTHOR

CloudflareDev

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL16m ago

DeepInfra launches serverless GLM-5.2 API

DeepInfra has launched serverless API support for Z.ai's GLM-5.2, a 753-billion parameter flagship model with a 1-million-token context window and configurable reasoning modes. Hosting the MIT-licensed model on its infrastructure allows developers to integrate GLM-5.2 into agentic workflows without managing massive model weights.

MODEL20m ago

Developer testing of Zhipu AI's newly released GLM-5.2 model reveals "on another level" capabilities for complex coding tasks and agentic workflows.

Harrison Kinsley (Sentdex) shared early praise for Zhipu AI's newly launched GLM-5.2 model, noting it performed well enough on initial tasks to become his primary coding model over the weekend. Released on June 13, 2026, by Zhipu AI (internationally Z.ai), GLM-5.2 is a flagship open-weights AI model designed for long-horizon software engineering and agentic workflows. It boasts a stable 1-million-token context window and adjustable "thinking-effort" levels to optimize for complex multi-step reasoning, with weights set to be open-sourced under the MIT License.

UPDATE23m ago

GLM-5.2 lands on Vercel AI Gateway

Vercel has added Z.ai's GLM-5.2 open-source model, featuring a 1-million-token context window, to its AI Gateway. The model is optimized for long-horizon engineering tasks and scored up to 96% on Next.js benchmarks when combined with agentic workflows.

Cloudflare Workers AI adds GLM 5.2