LLMPrice
Updated daily
Direct API pricing comparison

Claude Opus 5 vs Claude Haiku 4.5

Compare current direct API token prices and estimated monthly workload costs for Claude Opus 5 and Claude Haiku 4.5.

2direct models
Pricing only.Claude Haiku 4.5 is cheaper in 4 of 4 comparable standard workload presets below. This is a pricing comparison only; it does not rank model quality.
Published direct rates

Token pricing side by side

USD per 1M text tokens
ModelInputCachedOutputContextMax outputSource
Claude Opus 5Anthropic · Direct API
$5$0.5$251M128KDirect
Claude Haiku 4.5Anthropic · Direct API
$1$0.1$5200K64KDirect
Monthly estimates

Same workload, different API bill

These four presets use 30 active days, standard direct rates, no retries, no reasoning-token add-on, no cache writes, and the cached-input percentage shown in each row.

Standard workloadClaude Opus 5Claude Haiku 4.5Lower monthly estimate
Chat10,000/day · 2,000 in · 500 out · 25% cached$6,075$1,215Claude Haiku 4.5 by $4,860 / mo
Coding2,000/day · 12,000 in · 1,800 out · 55% cached$4,518$903.6Claude Haiku 4.5 by $3,614.4 / mo
Agent1,200/day · 32,000 in · 2,500 out · 65% cached$4,640.4$928.08Claude Haiku 4.5 by $3,712.32 / mo
Documents400/day · 180,000 in · 2,000 out · 15% cached$9,942$1,988.4Claude Haiku 4.5 by $7,953.6 / mo
Custom workload

Use your own traffic

The main calculator includes batch mode, long-context rules, retries, reasoning tokens, cache writes, and other model-specific pricing logic that a static comparison cannot fully capture.

Related comparisons

Compare nearby alternatives