Models · Anthropic · Out sinceReleased 15 Oct 2025

Claude Haiku 4.5

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary

Where you can use it:In apps:Claude (Team plan) · Haiku 4.5

Claude Haiku 4.5 is made by Anthropic. We don't have enough test results yet to rank it. It's mid-priced to use.

Current cheap tier (claude-haiku-4-5-20251001). Extended thinking (budget), effort parameter not supported. Haiku 5.5 announced as "coming weeks" in the Opus 5.5 post.

Writing & creativity: —
Research & analysis: —
Coding: —
Price: Mid-priced$1 / $5
Price per 1M (blended)Blended / 1M: $2
MemoryContext: 200K
Longest answerMax output: 64K
Test resultsResults: 6 (6 independent6 indep.)
Out sinceReleased: 15 Oct 2025
Made byVendor: Anthropic
UnderstandsInputs: text, image

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as anthropic/claude-haiku-4.5.

Route it as anthropic/claude-haiku-4.5 at $1 in / $5 out per 1M tokens, 200K context. Listed since 15 Oct 2025.

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
						NotesNotes
ProgramBench (avg test pass rate)	30.0%	Default	Independent testIndependentProgramBench ↗	28 Sep 2026	mini-SWE-agent	avg behavioral-test pass rate ("Score" column); fully resolved 0.0%, almost (>=95% tests) 0.0%; avg cost $0.80/task
ProgramBench (fully resolved)	0.0%	Default	Independent testIndependentProgramBench ↗	28 Sep 2026	mini-SWE-agent	strict fully-resolved rate; almost (>=95% tests) 0.0%; avg cost $0.80/task
SWE-bench Multilingual	64.7%	Default	Independent testIndependentSWE-bench ↗	13 Feb 2026	mini-SWE-agent 2.0.0a0	Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
SWE-Bench Pro V2 (hard)	25.5%	Extra highHaiku 4.5 (Claude Code) xhigh	Independent testIndependentScale AI SEAL ↗	1 Oct 2026	Claude Code	rank 11 (Scale rank accounts for CI); ±0; entry added 2026-09-22; SWE-Bench Pro V2 (642 tasks, locked protocol, released 2026-09-22)
SWE-bench Verified (bash-only, mini-SWE-agent)	66.6%	High	Independent testIndependentSWE-bench ↗	17 Feb 2026	mini-SWE-agent 2.0.0	Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
Vectara Hallucination Leaderboard (HHEM)	9.8%	Defaultanthropic/claude-haiku-4-5-20251001	Independent testIndependentVectara ↗	22 Sep 2026	—	factual consistency 90.2 %; answer rate 99.5 %; avg summary 115.1 words; HHEM-2.3 judge; effort not stated (API default)