Claude Haiku 4.5 vs Claude Sonnet 4.6

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Claude Haiku 4.5

Anthropic · Oct 2025

Anthropic's fast tier: Sonnet-4-class coding performance at $1/$5 and more than twice the speed.

Claude Sonnet 4.6

Anthropic · Apr 2026

Anthropic's mid-tier workhorse: near-Opus capability at $3/$15, and the leader on the Finance Agent benchmark.

The verdict

Claude Sonnet 4.6 wins 1 of the 1 benchmarks these models share, against 0 for Claude Haiku 4.5. On price the gap is dramatic: Claude Haiku 4.5 works out roughly 3.0x cheaper per blended million tokens. Claude Sonnet 4.6 also takes 1M of context versus 200K for Claude Haiku 4.5.

Benchmark head-to-head 01

SWE-bench Verified
73.3%~79.6%
Claude Haiku 4.5Claude Sonnet 4.6

Specs & pricing

Claude Haiku 4.5Claude Sonnet 4.6
modhub Index
Input price / 1M$1$3
Output price / 1M$5$15
Context window200K1M
Max output64K64K
Open weightsnono
Reasoning modelyesyes
Multimodal inputtext, imagetext, image
Knowledge cutoffFeb 2025Jan 2026
ReleasedOct 2025Apr 2026
Example monthly cost*$17.50$52.50

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Claude Haiku 4.5 or Claude Sonnet 4.6?
Claude Sonnet 4.6 wins 1 of the 1 benchmarks these models share, against 0 for Claude Haiku 4.5. On price the gap is dramatic: Claude Haiku 4.5 works out roughly 3.0x cheaper per blended million tokens. Claude Sonnet 4.6 also takes 1M of context versus 200K for Claude Haiku 4.5.
Which is cheaper, Claude Haiku 4.5 or Claude Sonnet 4.6?
Claude Haiku 4.5 costs $1/$5 per million input/output tokens, while Claude Sonnet 4.6 costs $3/$15. For a typical workload of 10M input and 1.5M output tokens per month, that's $17.50 versus $52.50.
Which model is better for coding, Claude Haiku 4.5 or Claude Sonnet 4.6?
On SWE-bench Verified — the standard agentic-coding benchmark — Claude Sonnet 4.6 scores ~79.6% versus 73.3% for Claude Haiku 4.5, making Claude Sonnet 4.6 the stronger pick for coding agents.

More comparisons