Claude Haiku 4.5 vs GPT-4.1

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.

GPT-4.1

OpenAI · Apr 2025

A non-reasoning workhorse with a 1M-token context window, still popular for predictable-latency production APIs.

The verdict

Claude Haiku 4.5 wins 2 of the 2 benchmarks these models share, against 0 for GPT-4.1. Claude Haiku 4.5 is about 1.8x cheaper per blended million tokens (3:1 input:output mix). GPT-4.1 also takes 1M of context versus 200K for Claude Haiku 4.5.

Benchmark head-to-head 20

SWE-bench Verified
73.3%54.6%
Claude Haiku 4.5GPT-4.1
GPQA Diamond
~73%66.3%
Claude Haiku 4.5GPT-4.1

Specs & pricing

Claude Haiku 4.5GPT-4.1
modhub Index
Input price / 1M$1$2
Output price / 1M$5$8
Context window200K1M
Max output64K33K
Open weightsnono
Reasoning modelyesno
Multimodal inputtext, imagetext, image
Knowledge cutoffFeb 2025Jun 2024
ReleasedOct 2025Apr 2025
Example monthly cost*$17.50$32.00

* 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 GPT-4.1?
Claude Haiku 4.5 wins 2 of the 2 benchmarks these models share, against 0 for GPT-4.1. Claude Haiku 4.5 is about 1.8x cheaper per blended million tokens (3:1 input:output mix). GPT-4.1 also takes 1M of context versus 200K for Claude Haiku 4.5.
Which is cheaper, Claude Haiku 4.5 or GPT-4.1?
Claude Haiku 4.5 costs $1/$5 per million input/output tokens, while GPT-4.1 costs $2/$8. For a typical workload of 10M input and 1.5M output tokens per month, that's $17.50 versus $32.00.
Which model is better for coding, Claude Haiku 4.5 or GPT-4.1?
On SWE-bench Verified — the standard agentic-coding benchmark — Claude Haiku 4.5 scores 73.3% versus 54.6% for GPT-4.1, making Claude Haiku 4.5 the stronger pick for coding agents.

More comparisons