Z.ai GLM-5.3 now available on Workers AI
Cloudflare has released Z.ai's GLM-5.3 agentic coding model on Workers AI with substantial performance improvements over GLM-5.2, including 50% gains on Z.ai Code Bench and 6x improvements on Terminal Bench 3.0, while maintaining the same pricing of $1.40 per M input tokens and $4.40 per M output tokens.
@cf/zai-org/glm-5.3 is now available on Workers AI. It is Z.ai's flagship agentic coding model, built for long-running, tool-driven development workflows rather than single-turn chat.
GLM-5.3 uses the same base model as GLM-5.2, with every gain coming from post-training. The results are substantial on coding and agentic benchmarks: Z.ai reports ↗ a 50% improvement over GLM-5.2 on its in-house Z.ai Code Bench, and calls GLM-5.3 the most capable open-weights model for coding. On public benchmarks, it scores 88.2 on Terminal Bench 2.1 (up from 81.0), 28.3 on Terminal Bench 3.0 — open-source state of the art, up from 4.6 — 66.9 on DeepSWE (up from 46.2), 78.1 on FrontierSWE (up from 67.5), and 42.5 on SWE-Marathon (up from 19.4). It is also the top-scoring model in Z.ai's comparisons on CyberGym for vulnerability discovery (84.5) and on long-horizon automation tasks like AutomationBench (48.2).
The price-to-performance ratio is the compelling part. On Workers AI, GLM-5.3 costs the same as GLM-5.2 — $1.40 per M input tokens, $0.26 per M cached input tokens, and $4.40 per M output tokens — while roughly doubling GLM-5.2's scores on long-horizon benchmarks like SWE-Marathon, and improving them by more than 6x on Terminal Bench 3.0.
GLM-5.3 requires the Workers Paid plan or prepaid AI Gateway credits.
Use GLM-5.3 through the Workers AI binding (env.AI.run()), the REST API, the OpenAI-compatible endpoint, or AI Gateway.
For more information, refer to the GLM-5.3 model page and pricing.
Source: original entry ↗
More from Cloudflare
Follow Cloudflare to get its new changes in your feed and email digest.
DNS - Configure Advanced Custom Nameservers with nameserver sets
Nameserver sets are now available in beta for Enterprise accounts, allowing you to group custom nameserver names with Cloudflare-assigned IP addresses and assign them to multiple zones. This new approach replaces legacy custom_ns sets with reusable, immutable objects that support up to 3 IPv4 and 3 IPv6 addresses per nameserver and can leverage Advanced anycast network groups for improved resiliency.
Emergency WAF managed rule for active RCE vulnerability
Cloudflare released an emergency WAF update with a new managed rule to block exploitation of a critical remote code execution vulnerability in popular web frameworks. The Generic Rules - Remote Code Execution detection prevents attackers from executing arbitrary system commands via malicious input with invalid path sequences.
Cloudflare API MCP server sends Workers Issues as MCP Events
The Cloudflare API MCP server now exposes Workers Issues as MCP Events through webhook subscriptions, allowing agents to receive real-time notifications when production failures are detected without polling. Clients can subscribe to cloudflare.alert.workers_observability_real_time_issue scoped to an account or individual Worker.