/radio 🍓☀️

Learn more about API rate limits in the Claude Platform docs. platform.claude.com/docs/en/…

Advancement through rate limit tiers is automatic. To manually request a higher rate limit, click "Request rate limit increase" in the Claude Console.

Each rate limit tier offers the same requests per minute and token throughput across the latest Opus, Sonnet, and Haiku models. This lets you choose the right model for the task, instead of making trade-offs for rate limiting.

We've raised Claude Platform API rate limits for all users and simplified the tiers, which are no longer based on API spend. The latest Sonnet and Haiku models now provide 5x higher rate limits at the highest tier.

Read more in the docs: code.claude.com/docs/en/arti…

Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, publishes it live to claude.a‍i, and updates it in real time while it keeps working. Pages are private to your account and fully self-contained.

Announcing Built with Claude: Life Sciences, a global virtual hackathon. Join us and @GladstoneInst for a week of researching and building with Claude Science and Claude Code, with a prize pool of $100k in credits.

Now that Fable 5 is ready to build (again), we've reset everyone's 5-hour and weekly rate limits.

Following conversations with the US government, we’ve updated our cybersecurity safeguards. The vast majority of coding work is unaffected. In the near term, the new safeguards will flag a slightly higher fraction of harmless requests than the previous Fable safeguards; we’re working to refine these over the coming weeks. Users will be clearly notified when a request is flagged, and they’ll instead receive a response from Opus 4.8. Our biology and chemistry classifiers are unchanged from our initial launch. These are still broader than we would like; they trigger fallbacks to Opus 4.8 on basic biology-adjacent questions. Improvements to these classifiers are landing soon.

Fable 5 is back.

Finally, we've added a new Managed Agents Observability tab in Console. This provides session-level metrics such as input/output token use and tool usage.

To learn more about these features, you can ask Claude Code using our built-in "claude-api" skill and check out our cookbook: github.com/anthropics/claude…

Agent Overrides let you start a session from a stored agent and override parts of its config for that one session: swap out the model, system prompt, tools, mcp_servers, or skills.

We’ve added a few updates to Claude Managed Agents: Streaming session event deltas, per-session agent overrides, new webhook event types, reverse pagination, and credential injection scoping.

Read more in the docs and prompting guide: platform.claude.com/docs/en/…

Sonnet 5 is a clear upgrade from 4.6, and the claude-api skill makes the migration even easier. This skill tunes prompts for Sonnet 5, recommends effort levels, and configures advisor mode. platform.claude.com/docs/en/…

Similarly, use multi-agent in Claude Managed Agents to mix Sonnet 5 and higher capacity sub-agents in order to delegate work to the right level of intelligence. platform.claude.com/docs/en/…

Sonnet 5 works well in multi-model setups. Have a more capable model plan while Sonnet 5 executes, or flip it with the Advisor strategy so Sonnet 5 only calls one when it gets stuck. platform.claude.com/docs/en/…

Sonnet 5 also holds up better in agents that run unattended. It keeps state across many steps, recovers from errors without losing the thread, and checks its own work as it goes. More multi-step runs finish correctly the first time.