Claude Haiku

Full Claude Platform available on Google Cloud (Anthropic managed)

Claude Models on Google Cloud (Anthropic managed) is generally available with US and Global endpoints. It gives Google Cloud customers the full Claude Platform feature set with Google Cloud IAM, billing and commitment drawdown. Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5 are available, and fast mode for Opus 5.5 costs $8 / $40 per million input and output tokens there.

Claude Code makes Haiku 5.5 the default Haiku model

Claude Code 2.1.293 added Claude Haiku 5.5 as the default Haiku model on the Anthropic API.

Claude Haiku 5.5 released at a much lower price than Haiku 4.5

Claude Haiku 5.5 launched with a 1M token context window at $0.10 / $0.50 per million tokens for prompts up to 100,000 tokens and $0.50 / $2.50 above that. Haiku 4.5 costs $1 / $5.

Claude Haiku 5.5 rejects budget thinking, sampling parameters and prefill

Manual extended thinking, temperature, top_p, top_k and assistant prefill can each return a 400 error on Haiku 5.5, and adaptive thinking is on by default.

Action needed:

Follow the Haiku 5.5 migration guide before switching model IDs.

Claude Haiku 5.5 available in GitHub Copilot

Claude Haiku 5.5 is available on Copilot Pro, Pro+, Max, Business and Enterprise at provider list price.

New API accounts can no longer edit context around thinking blocks

To counter distillation, the API now checks that a thinking block is sent back with the same system prompt, tools and messages. On Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5, accounts created on or after August 31, 2026 get an error unless they opt into dropping the block.

Action needed:

Use server-side compaction or mid-conversation tool changes, or opt into non-strict mode.

Claude Haiku 3 retired

Action needed:

Switch to Claude Haiku 4.5 or Haiku 5.5.

Claude in Amazon Bedrock opens to all Bedrock customers