Claude Code Adds Claude Haiku 5.5 as the Default Haiku Model
Claude CodeClaude Code 2.1.293 adds Claude Haiku 5.5 (claude-haiku-5-5), which is now the default Haiku model on the Anthropic API. The model offers a 1M-token context window and is priced at $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100K tokens. Prompts over 100K tokens cost $0.50 and $2.50. That is a large price cut from Haiku 4.5, which cost $1 and $5 per million tokens.
Key Takeaways
- Claude Haiku 5.5 becomes the default Haiku model on the Anthropic API, so Claude Code's Haiku tier upgrades automatically.
- Pricing drops sharply to $0.10 input and $0.50 output per million tokens for prompts up to 100K tokens, compared with $1 and $5 for Haiku 4.5.
- A 1M-token context window brings long-context work to the smallest and cheapest model in the lineup.
- Long prompts cost more: prompts over 100K tokens are billed at $0.50 and $2.50 per million tokens.
- A good fit for sub-agents, where cheap, fast helpers can take on search and summarization while larger models handle hard reasoning.
- Claude Code 2.1.293 or newer is required to use
claude-haiku-5-5.
Sources & Mentions
1 external resource covering this update
A New Default Haiku
Claude Code 2.1.293 adds Claude Haiku 5.5, identified by the model ID claude-haiku-5-5, and makes it the default Haiku model on the Anthropic API. Anyone who selects the Haiku tier in Claude Code, or who runs small helper tasks on it, now gets the new model without changing configuration.
Context Window and Pricing
Haiku 5.5 supports a 1M-token context window, a large step up for the smallest model in the lineup. Pricing is $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100K tokens. For prompts over 100K tokens, the rates are $0.50 and $2.50 per million tokens. Haiku 4.5 charged $1 and $5 at every prompt size, so typical short-context work costs a fraction of what it did before.
Where It Fits in Claude Code
The low price and speed make Haiku 5.5 a natural fit for high-volume, lower-stakes work in Claude Code: sub-agents that search or summarize, quick lookups, and repetitive edits that do not need a larger model's depth. Launch-day coverage describes it as the first Haiku with adjustable thinking levels, running from Low to Max. It can sit under larger models such as Opus 5.5 and Sonnet 5.5 as a helper while those models handle the harder reasoning.
Updating
The model requires Claude Code 2.1.293 or newer. Running claude --version confirms the installed version.