Releasesby GlyphAccess - Code Mode for MCP server portals
MCP server portals support Code Mode MCP server patterns , a technique that reduces context window usage by replacing individual tool definitions with a single code execution tool. Code Mode is turned on by default on all portals. To turn it off, edit the portal in Access controls > AI controls and turn off Code Mode under Basic information .
Also shipped Mar 26, 2026Cloudflare in March 2026 →
Mutual Exclusivity
What it is: Grouping guides and surveys into a mutual exclusivity set ensures each end-user sees at most one from the group. The primary use case is platform-specific announcements: create a version for iOS and another for Android, add both to the group, and users see only the version that matches their device.
Temperature Parameter: Increased Maximum The maximum allowed value for the temperature parameter for Chat...
Temperature Parameter: Increased Maximum The maximum allowed value for the temperature parameter for Chat Completions has been increased from 1.5 to 2.0. This aligns with the range supported by OpenAI, Fireworks, and other major LLM providers. Higher temperature values produce more random and creative outputs.
developer Message Role (gpt-oss-120b) The Chat Completions API now supports the developer message role for...
developer Message Role (gpt-oss-120b) The Chat Completions API now supports the developer message role for gpt-oss-120b, aligning with the OpenAI API message format. The developer role is functionally equivalent to system , the system role remains supported for backwards compatibility. Other models do not support the developer role.
TTS speak speed (Early Access)
You can now control the speaking rate of Deepgram TTS in the Voice Agent API using the agent.speak.provider.speed parameter. This parameter accepts a float value between 0.7 and 1.5 , with 1.0 as the default.
Updated LLM models
New OpenAI models , Two new models are now available in the Standard pricing tier: gpt-5.4-nano gpt-5.4-mini Gemini 2.0 Flash deprecated , The gemini-2.0-flash model is now deprecated. We recommend migrating to gemini-2.5-flash or a newer Gemini model. See the Google models table for alternatives.
More from Cloudflare developer platformEvery Cloudflare developer platform release →
Access - Context optimization for MCP server portals
MCP server portals support two context optimization options that reduce how many tokens tool definitions consume in the model's context window. Both options are activated by appending the optimize_context query parameter to the portal URL. minimize_tools Strips tool descriptions and input schemas from all upstream tools, leaving only their names.
Containers - Easily connect Containers and Sandboxes to Workers
Containers and Sandboxes now support connecting directly to Workers over HTTP. This allows you to call Workers functions and bindings , like KV or R2 , from within the container at specific hostnames. Run Worker code Define an outbound handler to capture any HTTP request or use outboundByHost to capture requests to individual hostnames and IPs.
Data Loss Prevention - Streaming ZIP file scanning removes per-file size limits
DLP now processes ZIP files using a streaming handler that scans archive contents element-by-element as data arrives. This removes previous file size limitations and improves memory efficiency when scanning large archives. Microsoft Office documents (DOCX, XLSX, PPTX) also benefit from this improvement, as they use ZIP as a container format.
Durable Objects, Workers - Access Durable Object jurisdiction via `ctx.id.jurisdiction`
ctx.id.jurisdiction inside a Durable Object now reports the jurisdiction the object was created in , for example "eu" when accessed through env.MY_DURABLE_OBJECT.jurisdiction("eu") , so you can make region-aware decisions without passing the jurisdiction through method arguments or persisting it in storage.
Radar - URL Scanner improvements on Cloudflare Radar
Radar ships several improvements to the URL Scanner ↗ that make scan reports more informative and easier to share: Live screenshots , the summary card now includes an option to capture a live screenshot of the scanned URL on demand using the Browser Rendering API.
Workers - New RFC 9440 mTLS certificate fields in Workers
Four new fields are now available on request.cf.tlsClientAuth in Workers for requests that include a mutual TLS (mTLS) client certificate. These fields encode the client certificate and its intermediate chain in RFC 9440 ↗ format , the same standard format used by the Client-Cert and Client-Cert-Chain HTTP headers , so your Worker can forward them directly...
Data Loss Prevention - Detect and sanitize HAR files
HTTP Archive (HAR) files are used by engineering and support teams to capture and share web traffic logs for troubleshooting. However, these files routinely contain highly sensitive data , including session cookies, authorization headers, and other credentials , that can pose a significant risk if uploaded to third-party services without being reviewed or...
logpush, Logs - Logpush , More granular timestamps
Logpush now supports higher-precision timestamp formats for log output. You can configure jobs to output timestamps at millisecond or nanosecond precision. This is available in both the Logpush UI in the Cloudflare dashboard and the Logpush API .