Blog
2 min read

Claude Sonnet 5.5 Released — and Its Cache Reads Just Got Cheaper

Claude Sonnet 5.5 arrived on 28 September 2026 at $2/$10 per million tokens, available on the Claude API, Bedrock, Google Cloud and Microsoft Foundry. On 7 October its prompt-cache read price was halved to $0.10. The breaking changes from Sonnet 5, and what it means for apps and Claude Code users.

Anthropic released Claude Sonnet 5.5 on 28 September 2026, the second model in the Claude 5.5 family after Opus 5.5. It's available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud and Claude in Microsoft Foundry.

Then on 7 October, Anthropic halved its cache read price from $0.20 to $0.10 per million tokens.

Pricing

Per million tokens Sonnet 5.5
Input $2
Output $10
5-minute cache write $2.50
Cache read $0.10 (0.05x input)
Batch input / output $1 / $5

That cache price matters most for apps that resend a long system prompt, documents or conversation history on every call — chatbots, agents and RAG apps. Reads from cache now cost a twentieth of normal input. (Prompt Caching Explained)

Breaking changes from Sonnet 5

  • To turn off up-front thinking, use thinking: {"type": "between_tools"}.
  • Forced tool use returns a 400 error. If your code sets tool_choice to a specific tool, rework it.
  • The older computer_20251124 tool isn't accepted on the Claude API or Google Cloud — move to the computer use toolset.

Anthropic's migration guide covers each change. Run your evals before switching production traffic. (Evaluate LLM Outputs)

In Claude Code

The sonnet alias now resolves to Sonnet 5.5 on the Anthropic API, with a default effort of medium. Switch with /model sonnet for everyday work that doesn't need Opus. (How to Change the Model in Claude Code)

Also announced

Anthropic announced that Claude Sonnet 4.5 (claude-sonnet-4-5-20250929) will be retired on 30 November 2026, recommending Sonnet 5.5 as the replacement. (Sonnet 4.5 Retirement)

What to do

  • On Sonnet 5 or 4.x via the API: test Sonnet 5.5, fix forced tool use, then switch.
  • Using caching heavily: your bill on Sonnet 5.5 just dropped further.

Source: Claude Platform release notes

EasySpawn gives your AI app a server-side backend where prompt caching, model switches and API keys are handled properly, with Claude Code to make the upgrade. See how it works or join the waitlist.

Related: Claude Opus 5.5 Released · Claude API Pricing Explained · Structured Output From LLMs · What Is Function Calling?

Keep reading