AI Search adds six new Workers AI text generation models
AI Search now supports six additional text generation models on Workers AI, including DeepSeek, GPT-OSS, Qwen, and Kimi models. These models are available for selection when creating or updating AI Search instances without requiring external provider keys.
AI Search now supports six additional Workers AI models for text generation:
| Model | Context window (tokens) |
|---|---|
@cf/deepseek-ai/deepseek-v4-flash-0731 |
1,048,576 |
@cf/deepseek-ai/deepseek-v4-pro-0813 |
1,048,576 |
@cf/openai/gpt-oss-120b |
128,000 |
@cf/openai/gpt-oss-20b |
128,000 |
@cf/qwen/qwen3.8-27b |
262,144 |
@cf/moonshotai/kimi-k2.7-code |
262,144 |
These models run on Workers AI, so they do not require an additional provider key. Select a model when creating or updating an AI Search instance in the dashboard or through the API.
For the full list of supported models, refer to Supported models.
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.