Claude Haiku 4.5vsGPT-5.1-Codex
Claude Haiku 4.5 is cheaper than GPT-5.1-Codex at $1/M vs $1.25/M input tokens.
| Spec | Claude Haiku 4.5 | GPT-5.1-Codex |
|---|---|---|
| Input price | $1/M tokens | $1.25/M tokens |
| Output price | $5/M tokens | $10/M tokens |
| Context window | 200K tokens | 400K tokens |
| Released | Oct 2025 | Nov 2025 |
| SWE-bench Verified | 73.3% | 73.7% |
Our Verdict
GPT-5.1-Codex
Claude Haiku 4.5Runner-up
Not enough votes to call it. On the specs, GPT-5.1-Codex has the edge: bigger model tier, bigger context window.
Pick Claude Haiku 4.5 for Web Design. Pick GPT-5.1-Codex for Reasoning.
Too close to call
API pricing
Cost per 1M tokens
Claude Haiku 4.5
Input
$1.00
1.3× cheaper
Output
$5.00
2.0× cheaper
GPT-5.1-Codex
Input
$1.25
Output
$10.00
Claude Haiku 4.5 is cheaper on both — 1.3× input, 2.0× output
Writing DNA
Style Comparison
Similarity
45%
Claude Haiku 4.5 uses 20.4x more emoji
Claude Haiku 4.5
GPT-5.1-Codex
61%Vocabulary70%
47wSentence Length17w
0.64Hedging0.39
5.1Bold3.4
6.3Lists3.5
0.20Emoji0.00
2.46Headings0.50
0.17Transitions0.38
Based on 24 + 14 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
GPT-5.1-Codex vs MiniMax M3New provider
GPT-5.1-Codex vs Ox AlphaNew provider
Claude Haiku 4.5 vs Gemini 2.5 Pro (I/O Edition)New provider
Claude Haiku 4.5 vs Gemini 2.5 Pro Preview 06-05New provider
GPT-5.1-Codex vs DeepSeek V3.1New provider
Claude Haiku 4.5 vs DeepSeek Prover V2New provider
Claude Haiku 4.5 vs DeepSeek R1New provider
Claude Haiku 4.5 vs DeepSeek R1 0528New provider