Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude Haiku 4.5 vs GPT-5.1-Codex

A detailed comparison of pricing, benchmarks, and capabilities

108 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Claude Haiku 4.5 wins:

  • Cheaper input tokens
  • Cheaper output tokens

GPT-5.1-Codex wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
Price Advantage
Claude Haiku 4.5
Benchmark Advantage
GPT-5.1-Codex
Context Window
GPT-5.1-Codex
Speed
GPT-5.1-Codex

Pricing Comparison

Price Comparison

MetricClaude Haiku 4.5GPT-5.1-CodexWinner
Input (per 1M tokens)$1.00$1.25 Claude Haiku 4.5
Output (per 1M tokens)$5.00$10.00 Claude Haiku 4.5
Cache Read (per 1M)$0.10$0.13 Claude Haiku 4.5
Cache Write (per 1M)$1.25N/A Claude Haiku 4.5
Using a 3:1 input/output ratio, Claude Haiku 4.5 is 42% cheaper overall.

Claude Haiku 4.5 Providers

No provider data available

GPT-5.1-Codex Providers

No provider data available

Benchmark Comparison

6
Benchmarks Compared
0
Claude Haiku 4.5 Wins
6
GPT-5.1-Codex Wins

Benchmark Scores

BenchmarkClaude Haiku 4.5GPT-5.1-CodexWinner
Intelligence Index
Overall intelligence score
31.143.1
Coding Index
Code generation & understanding
29.636.6
Math Index
Mathematical reasoning
39.095.7
MMLU Pro
Academic knowledge
80.086.0
GPQA
Graduate-level science
64.686.0
LiveCodeBench
Competitive programming
51.184.9
GPT-5.1-Codex significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude Haiku 4.5
Other models

Context & Performance

Context Window

Claude Haiku 4.5
200,000
tokens
GPT-5.1-Codex
400,000
tokens
GPT-5.1-Codex has a 50% larger context window.

Speed Performance

MetricClaude Haiku 4.5GPT-5.1-CodexWinner
Tokens/second113.2 tok/s131.9 tok/s
Time to First Token0.42s7.06s
GPT-5.1-Codex responds 17% faster on average.

Capabilities

Feature Comparison

FeatureClaude Haiku 4.5GPT-5.1-Codex
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Haiku 4.5GPT-5.1-Codex
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedOct 2025Nov 2025

Claude Haiku 4.5 Modalities

Input
imagetext
Output
text

GPT-5.1-Codex Modalities

Input
textimage
Output
text

Related Comparisons

Compare Claude Haiku 4.5 with:

Compare GPT-5.1-Codex with:

Frequently Asked Questions

Claude Haiku 4.5 has cheaper input pricing at $1.00/M tokens. Claude Haiku 4.5 has cheaper output pricing at $5.00/M tokens.
GPT-5.1-Codex scores higher on coding benchmarks with a score of 36.6, compared to Claude Haiku 4.5's score of 29.6.
Claude Haiku 4.5 has a 200,000 token context window, while GPT-5.1-Codex has a 400,000 token context window.
Claude Haiku 4.5 supports vision. GPT-5.1-Codex supports vision.