Post

Claude Haiku 5.5 is out, almost a year after Haiku 4.5. On paper, it was worth the wait. Per million tokens, for prompts up to 100K: Input: $0.10 (Haiku 4.5: $1) Output: $0.50 (Haiku 4.5: $5) Longer prompts cost half as much as on Haiku 4.5. Anthropic puts the average saving at around 75%.

IKcode | Igor Wnek

@ikcode.dev

I expect it to earn a place as a subagent on well-specified work: implementing a plan, triage in code review, codebase research. Sonnet and Opus keep complex agentic coding. Prompting guide tip: at low and medium effort it sometimes reports a change as done without running a check. Name the check.

7/10/26, 9:11 pm0 reposts1 like

IKcode | Igor Wnek

@ikcode.dev

Same update: Sonnet 5.5 cache reads drop from $0.20 to $0.10 per million tokens. Anthropic puts the saving at around 20% on most agentic work, in line with my own estimate. With Haiku taking the right subagent work, I expect my Claude Max plans to go much further.

IKcode | Igor Wnek

@ikcode.dev

GPT-6 Luna costs the same for shorter prompts. Anthropic's table puts Haiku 5.5 ahead, 39.2% vs 16.4% on Terminal-Bench 4.0. My guess: GPT-6.1 Luna lands tomorrow. GPT-6.1 Sol came the day after Sonnet 5.5. https://www.anthropic.com/claude-haiku-5-5