One Claude API deprecation hits Aug 5, 2026. Here's the plain-English checklist: what's breaking, what to swap it to, and what you can ignore.
Last updated: Jun 27, 2026
Anthropic retired both models on June 15, 2026. If you still call these model IDs in production, they're already failing — migrate immediately.
Heads up on Opus 4.8: Anthropic notes the current flagship may require prompt tweaks compared to Opus 4. It's a stronger model — better self-verification, better vision, better long-running agent behavior, and more honest about flagging what it's unsure of — but your existing Opus 4 prompts weren't necessarily tuned for it. Test before you ship.
Opus 4.1 reaches end of life on August 5, 2026. If you still pin this model ID anywhere — backend services, scripts, agents, Bedrock/Vertex configs — roll it forward to the current flagship, Opus 4.8, well before the date.
What to check: grep your repos and Bedrock/Vertex configs for the Opus 4.1 model ID. Opus 4.8 is a stronger model — better self-verification and more honest about its own work — but test your existing prompts in staging before you promote.
Sonnet 5 is the new default, but two things break existing code. First: if your calls set temperature or top_p, they now error on Sonnet 5 — remove those parameters before switching the model ID. Second: the new tokenizer produces up to about a third more tokens from the same text, so any token budgets or cost estimates calibrated on Sonnet 4.6 will undercount — recheck them.
The pricing window: promotional pricing of $2 / $10 per million tokens (input / output) runs through August 31, 2026. That makes this a cheap window to migrate and test before rates normalize.
What to check: grep for temperature and top_p in your Sonnet call sites; re-run any token-budget math against the new tokenizer in staging.
claude-sonnet-4-20250514, claude-opus-4-20250514, and claude-opus-4-1-20250805.If you're only using Claude in the web app (claude.ai), Projects, Cowork, or the Desktop app: nothing. Anthropic manages model selection on your behalf in those surfaces. You're already on the latest models.
If you're using Claude Code: nothing. Claude Code picks models automatically based on the task — it's already migrated.
If you're on Enterprise with SSO + managed models: check with your admin, but most Enterprise deployments auto-migrate.
Deprecations are going to keep happening. Anthropic ships a new flagship model roughly every two months, and older models get retired on a ~6–12 month cycle. The fastest teams build one migration runbook once and reuse it each cycle. If this page helped, we'll keep it current — bookmark it.