AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Haiku 4.5GPT-5.4 Nano (batch)
Claude Haiku 4.5

Anthropic

GPT-5.4 Nano (batch)

OpenAI

Pricing
Input $/1M$1.00$0.10
Output $/1M$5.00$0.625
Blended $/1M (3:1)$2.00$0.231
Cache read $/1M$0.10$0.01
Cache write $/1M$1.25
Quality indices
Intelligence Index16.920.7
Coding Index43.956.1
Math Index
Agentic Index816
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
GPQA Diamond81.7%
Humanity's Last Exam28.3%
SciCode47.2%
IFBench75.9%
AA-LCR (Long Context Reasoning)76.7%
Terminal-Bench Hard42.4%
Terminal-Bench 2.160.7%
τ²-Bench (Telecom)76.0%
τ³-Bench Banking27.4%
Design Arena (Elo)
Website1,135
UI components1,115
Data viz1,139
SVG1,049
3D1,101
Game dev1,120
Code categories1,130
ASCII art1,159
Specs
Context window200K400K
Max output tokens64K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT