Claude Opus 5.5 is live: pin the model id, then check the bill

UpdatedSeptember 22, 2026

Anthropic published Claude Opus 5.5 on September 22, 2026 — the first model in the Claude 5.5 family. On the Claude Platform the model id is claude-opus-5-5. It is also available on AWS, Google Cloud, and Microsoft Azure. The release page says Opus 5.5 performs at the level of Claude Fable 5.1 on most work, costs 40% less to run than Opus 5 on typical workloads, and returns output more than 30% faster than Opus 5.

That is a product you can pin, not a routing rumor. If you read the Opus 5.2 routing speculation note, keep the stories apart: that post was an unconfirmed routing idea; this one is the official page at https://www.anthropic.com/claude-opus-5-5.

This is an excerpt. Read the full post at otf-kit.dev/blog/claude-opus-5-5-builders — full-stack kits your AI coding agent can actually ship to production. Browse the kits →

#agents #architecture #ai-tools

Comments

Join the discussion

No comments yet. Be the first to comment.

More from this blog

Cursor Automations last mile: Security Review plus Rollouts, not hope-CI

Last-mile confidence is not a vibe and it is not “CI was green.” For Teams and Enterprise, Cursor Automations now cover the two gaps that still eat merge-and-ship weekends: exploitable-bug review on p

Sep 24, 20261 min read

Cursor Automations last mile: Security Review plus Rollouts, not hope-CI

Wire TanStack AI agents to OAuth-protected MCP via Vercel Connect

If you already run TanStack AI agents that call MCP tools, the boring failure mode is not that the model is dumb. It is that you pasted a long-lived MCP token into env, shipped it with the deployment,

Sep 24, 20261 min read

Wire TanStack AI agents to OAuth-protected MCP via Vercel Connect

Queue backpressure on an owned backend: refuse the burst before the pool melts

Agent runs, vendor webhook fan-out, and retry storms arrive as a sudden pile of HTTP calls on an API you operate. The database pool and the worker processes behind that API are a fixed budget. Once ev

Sep 24, 20261 min read

Queue backpressure on an owned backend: refuse the burst before the pool melts

Circuit breakers on an owned backend: fail fast when the AI vendor fails

When a downstream AI or vendor HTTP dependency starts failing, the owned API should stop waiting on it. A circuit breaker opens after a measured run of failures and returns a cached, stale, or degrade

Sep 24, 20261 min read

Circuit breakers on an owned backend: fail fast when the AI vendor fails

Park failed jobs in a DLQ with reason, snapshot, and replay — not silent drop

On an owned backend, a failed background job belongs in a dead-letter queue with a failure reason, a payload snapshot, an attempt count, timestamps, the original queue identity, and a human or agent r

Sep 23, 20261 min read

Park failed jobs in a DLQ with reason, snapshot, and replay — not silent drop

OTF — kits your AI coding agent can ship to production

642 posts

Engineering notes on shipping production apps with AI coding tools — Claude Code, Cursor, Codex, Lovable, Bolt — and the stack underneath: React Native, Expo, Next.js, Supabase. Honest takes on what works, what breaks, and the full-stack kits that get you to production faster. By OTF.

Command Palette

Comments

More from this blog