Skip to main content
AI Choice Engine

Anthropic

Claude Haiku 4.5

Claude Haiku 4.5 is a Anthropic model with 200K context, $1 in / $5 out per million tokens, last verified October 1, 2026. Open weights: no. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

Claude Haiku 4.5 is Anthropic's lower-cost Haiku tier for high-volume classification and extraction at $1/$5 per million input/output tokens.

Recorded profile verification October 1, 2026Individual provider fields may change

AI model specification details
SpecificationClaude Haiku 4.5
ProviderAnthropic
TierBudget
Context window200K
Max output64K
Input / 1M tokens$1
Output / 1M tokens$5
WeightsClosed
ParametersNot verifiedUnverified
Reasoning levelsextended thinking (budget_tokens)
Modalitiestext, image
API model idclaude-haiku-4-5-20251001
ReleasedOctober 15, 2025

Pricing tiers: Standard $1/$5 per MTok; cache reads $0.10, 5-minute writes $1.25 and 1-hour writes $2. Batch $0.50/$2.50. Context 200K and output 64K. Reliable knowledge cutoff Feb 2025; training cutoff Jul 2025. The alias claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Retirement not sooner than October 15, 2026; no definite shutdown is announced.

Publisher evidence

Published benchmark results

Each result keeps its source date visible. Dates refer to source publication or capture unless the source explicitly states when it measured the result. A missing benchmark is not treated as a zero.

Published benchmark results for Claude Haiku 4.5
BenchmarkScoreSource dateSource
SWE-bench Verified73.3%2025-10-15Anthropic — Introducing Claude Haiku 4.5 (vendor, avg of 50 trials, 128K thinking budget) · View source
SWE-bench Verified [high]mini-SWE-agent 2.0.0; bash-only, single attempt; published submission February17,202666.6%2026-02-17SWE-bench official submission metadata (66.6%, $0.330924/task; distinct from Anthropic vendor 73.3%) · View source
Terminal-Bench40.21%2025-10-15Anthropic — Introducing Claude Haiku 4.5 (vendor, Terminus 2, no thinking, 6 runs; 41.75 with 32K thinking) · View source

Best for

  • High-volume classification
  • Routine extraction
  • Latency-sensitive stacks

Watch out

No adaptive thinking (manual extended thinking via budget_tokens only); 200K context. Anthropic lists 2026-10-15 as the earliest possible retirement date, and Haiku 5.5 is announced but not released.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

Claude Haiku 4.5

Answered from the verified figures on this page rather than general guidance.

How much does Claude Haiku 4.5 cost per million tokens?
Claude Haiku 4.5 lists base rates of $1 per million input tokens and $5 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Standard $1/$5 per MTok; cache reads $0.10, 5-minute writes $1.25 and 1-hour writes $2. Batch $0.50/$2.50. Context 200K and output 64K. Reliable knowledge cutoff Feb 2025; training cutoff Jul 2025. The alias claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Retirement not sooner than October 15, 2026; no definite shutdown is announced.
What is Claude Haiku 4.5's context window?
Claude Haiku 4.5 accepts about 200K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Claude Haiku 4.5 best for?
Claude Haiku 4.5 is a budget tier from Anthropic. It suits high-volume classification, routine extraction, latency-sensitive stacks. No adaptive thinking (manual extended thinking via budget_tokens only); 200K context. Anthropic lists 2026-10-15 as the earliest possible retirement date, and Haiku 5.5 is announced but not released.
Model comparison catalogBenchmark library