The arena · AI model review

Claude Haiku 4.5

by Anthropic

Anthropic's fastest model: about 90% of Sonnet 4.5's coding skill at $1/$5 per 1M tokens, 200K context.

Arena score 3.6/567% recommended · 2 votes
Reasoning3.0
Coding3.5
Writing3.0
Speed4.5
Value4.0
Visit Claude Haiku 4.5high-volume, latency-sensitive API workloadssub-agent orchestration and agentic tool usescoped coding edits and code reviewreal-time chat assistants
Price

$5/1M out

Single tier: $1/1M input, $5/1M output; prompt cache reads $0.10/1M (5m writes $1.25/1M) and Batch API cuts 50% ($0.50/$2.50); no long-context surcharge (200K max).

Provider

Anthropic

Context window

200K tokens

Input price

$1/1M in

Output price

$5/1M out

Modalities

text, vision (input); text output

Open weights

No

What is Claude Haiku 4.5?

Small, speed-focused Claude model released October 15, 2025. Scores 73.3% on SWE-bench Verified, roughly 90% of Sonnet 4.5's agentic coding performance at one third of the cost. Supports vision input and extended thinking, with a 200K context window and 64K max output.

Claude Haiku 4.5 pros & cons

Pros

  • 73.3% on SWE-bench Verified, about 90% of Sonnet 4.5's agentic coding at one third of the price
  • Fast: more than 2x Sonnet 4 speed per Anthropic, with launch customers reporting 4-5x faster than Sonnet 4.5; ~92-110 output tok/s measured by Artificial Analysis
  • Devs report precise, localized code edits that avoid touching irrelevant code, better than GPT-5 mini class in early testing
  • Supports both vision input and extended thinking, rare at this price tier at launch
  • Well suited as worker model in multi-agent setups (Sonnet/Opus plans, parallel Haiku sub-agents execute)
  • Prompt caching reads at $0.10/1M and 50% Batch API discount cut effective cost further

Cons

  • $5/1M output is pricey for a small model: Gemini Flash and GPT mini tiers undercut it several-fold on output-heavy tasks
  • 200K context (vs 1M for Sonnet 5/Opus siblings) and 64K max output limit large-codebase and long-output work
  • Mediocre cross-domain reasoning: users report weak results on GPQA, MedQA, MMMU style knowledge tasks
  • Throughput varies widely in practice (82-208 tok/s reported) and quality degrades on long 7-8+ minute agentic sessions
  • Knowledge cutoff (reliable to Feb 2025) is dated by mid-2026 standards

The arena’s verdict

Pick Haiku 4.5 if you are on the Anthropic stack and need near-Sonnet coding quality at low latency and a third of the price: it is a massive step up from Haiku 3.5 and excels as the worker model in multi-agent pipelines. It remains Anthropic's current small model as of July 2026, so it is the default cheap tier for Claude-based products. Avoid it for deep cross-domain reasoning, very large codebases (200K context cap), or pure cost-per-token shopping, where Gemini Flash and GPT mini tiers are now cheaper, and step up to Sonnet 5 when quality matters more than speed.

Thumbs up or thumbs down

Cast your verdict

Would you recommend Claude Haiku 4.5, or warn the crowd away?

67%crowd score · 2

Top Claude Haiku 4.5 alternatives

All alternatives
1
Claude Opus 4.7

Anthropic's April 2026 Opus: 87.6% SWE-bench Verified, 1M context, high-res vision, now behind Opus 4.8

$25/1M out57%(3)
Visit
2
Claude Opus 4.8

Anthropic's flagship Opus-tier model for long-horizon agentic coding; 1M context at $5/$25 per 1M tokens.

$25/1M out57%(3)
Visit
3
Claude Sonnet 5

Anthropic's most agentic Sonnet: near Opus 4.8 quality on coding and agents at $3/$15 with 1M context

$15/1M out ($10 intro until 2026-08-31)57%(3)
Visit

Compare Claude Haiku 4.5 head-to-head

What the crowd says

Guardian of the Repo

The precise localized edits are the underrated feature. It fixes the line that needs fixing and leaves the rest alone. GPT mini class models keep rewriting half my file.

Champion of Vibes

Haiku 4.5 gives me about 90% of Sonnet agentic coding at a third of the price, and it is fast enough that edit loops feel instant. My default for quick fixes now.

Claude Haiku 4.5: frequently asked questions

How much does Claude Haiku 4.5 cost per 1M tokens?

Claude Haiku 4.5 costs $1/1M in per 1M input tokens and $5/1M out per 1M output tokens. Single tier: $1/1M input, $5/1M output; prompt cache reads $0.10/1M (5m writes $1.25/1M) and Batch API cuts 50% ($0.50/$2.50); no long-context surcharge (200K max).