Claude Haiku 4.5
Anthropic's fastest tier — 61.4% on DualEntry, strong for high-volume classification at $1/$5 per MTok.
Accounting overall
61.4%
Input / Output
$1.00 / $5.00 per MTok
Context
200K
Speed
~200 tok/s
Released
2025-10
Cutoff
2025-07
Eight accounting-task categories borrowed from DualEntry's 101-task benchmark. Measured where published, synthesized from adjacent benchmarks otherwise.
Haiku 4.5 is the right choice for high-volume, latency-sensitive, narrow-scope accounting workloads — invoice classification, transaction categorization, simple extraction. At 61.4% DualEntry overall it's not going to autonomously run a month-end close, but its structured-task scores (transaction classification in particular) are competitive.
Pricing correction note: prior editions of this profile listed Haiku 4.5 at $0.25/$1.25 per MTok, which is Haiku 3-era pricing. Anthropic's published Haiku 4.5 pricing is $1.00 input / $5.00 output per MTok — four times higher than the prior value. That changes the value-per-dollar story materially: Haiku 4.5 remains substantially cheaper than Opus 4.7, but the ratio is closer to 5x than the 20x the prior pricing implied.
The 200K context is the meaningful limiter vs the 1M-context alternatives. For high-volume workflows that don't need long context, that's fine.
Citations
- DualEntry benchmark (Haiku 4.5 61.4%)dualentry.com/blog/claude-opus-4-7-accounting-ai-benchmark-results
- Anthropic — Claude Haiku 4.5 pricing ($1 input / $5 output per MTok)platform.claude.com/docs/en/about-claude/pricing
- Anthropic — Introducing Claude Haiku 4.5anthropic.com/news/claude-haiku-4-5