Anthropic Claude API pricing

Models: 12; 3 scored
Cheapest call: $0.0038; Claude Haiku 5.5
Dearest call: $0.3829; Claude Fable 5.1
Best bugs caught: 90%; Claude Opus 5.5
Newest: 2026-10-07; Claude Haiku 5.5

Pricing

Anthropic models' list prices per 1M tokens, one review call and reading a pull request.
				Cache write / 1M
Claude Haiku 5.5Above 100K in: $0.50 / $2.50	$0.10	$0.50	$0.01	$0.125	$0.0038	$0.0026
Claude Haiku 4.5	$1.00	$5.00	$0.10	$1.25	$0.0383	$0.0262
Claude Sonnet 5.5	$2.00	$10.00	$0.10	$2.50	$0.0766	$0.0524
Claude Sonnet 5	$2.00	$10.00	$0.20	$2.50	$0.0766	$0.0524
Claude Sonnet 4.6	$3.00	$15.00	$0.30	$3.75	$0.1149	$0.0786
Claude Opus 5.5	$4.00	$20.00	$0.20	$5.00	$0.1532	$0.1048
Claude Opus 5	$5.00	$25.00	$0.50	$6.25	$0.1915	$0.131
Claude Opus 4.8	$5.00	$25.00	$0.50	$6.25	$0.1915	$0.131
Claude Opus 4.7	$5.00	$25.00	$0.50	$6.25	$0.1915	$0.131
Claude Opus 4.6	$5.00	$25.00	$0.50	$6.25	$0.1915	$0.131
Claude Fable 5.1	$10.00	$50.00	$0.25	$12.50	$0.3829	$0.2621
Claude Fable 5	$10.00	$50.00	$1.00	$12.50	$0.3829	$0.2621

Benchmark

Benchmark results
Compare
	1=	Claude Opus 5.5Anthropic · Frontier	90%	93%	98%	1.7	$0.1525	$0.1921	33s
	1=	Claude Sonnet 5.5Anthropic · Mid-range	77%	81%	100%	2.0	$0.0571	$0.083	11s
	1=	Claude Haiku 5.5Anthropic · Economy	64%	67%	98%	1.4	$0.0038	$0.0064	15s

By language and bug kind

Share of known bugs each model caught, by language
Model	All	TypeScript6 bugs	Go4 bugs	Java4 bugs	Rust4 bugs	C#3 bugs	JavaScript3 bugs	Kotlin3 bugs	PHP3 bugs	Python3 bugs	Ruby3 bugs	Swift3 bugs	C++2 bugs	C1 bug
Claude Opus 5.5	90%	100%	50%	78%	100%	100%	100%	67%	100%	100%	89%	100%	100%	100%
Claude Sonnet 5.5	77%	83%	50%	45%	100%	56%	100%	67%	67%	67%	100%	100%	100%	100%
Claude Haiku 5.5	64%	83%	75%	40%	75%	67%	33%	67%	100%	39%	67%	67%	50%	0%

Quality against cost

Higher catches more · further left is cheaper

AnthropicFaded: models outside this list95% range: the line through each point

Every point as a table

Bugs caught and measured cost per review, by model
Model	Bugs caught	95% range	Cost / review
Claude Opus 5.5	90%	81%–97%	$0.1525
Claude Sonnet 5.5	77%	64%–89%	$0.0571
Claude Haiku 5.5	64%	50%–78%	$0.0038

Other benchmarks

Outside benchmarks by model
Model	Arena WebDev	Arena Agent	Epoch Capabilities Index
Claude Fable 5.1	1741Max · range 1732 to 1751	0.140Max · range 0.120 to 0.160	165range 162 to 169
Claude Fable 5	1625High · range 1619 to 1631	0.082High · range 0.068 to 0.096	162range 160 to 166
Claude Opus 5.5	1807Max · range 1793 to 1822	0.189Max · range 0.161 to 0.216	167range 164 to 171
Claude Opus 5	1689Max · range 1683 to 1696	0.087Max · range 0.070 to 0.104	163range 160 to 166
Claude Opus 4.8	1556High · range 1550 to 1561	–	158range 156 to 161
Claude Opus 4.7	1558High · range 1552 to 1563	–	156range 155 to 159
Claude Opus 4.6	1547High · range 1541 to 1552	–	155range 154 to 157
Claude Sonnet 5.5	1768xHigh · range 1754 to 1781	0.130Max · range 0.099 to 0.161	165range 161 to 168
Claude Sonnet 5	1541High · range 1535 to 1547	0.046High · range 0.029 to 0.063	156range 154 to 159
Claude Sonnet 4.6	1523range 1518 to 1528	–	152range 150 to 155
Claude Haiku 5.5	1585High · range 1573 to 1596	0.015High · range 0.005 to 0.024	159range 157 to 162
Claude Haiku 4.5	1330range 1325 to 1335	–	142range 139 to 144

Source: LMArena CC BY 4.0, Oct 16, 2026 · Epoch AI CC BY 4.0, Oct 7, 2026

Families

Other makers

Related lists

Updated Oct 16, 2026All prices pricing.json