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 Nano
Claude Haiku 4.5

Anthropic

GPT-5 Nano

OpenAI

Pricing
Input $/1M$1.00$0.05
Output $/1M$5.00$0.40
Blended $/1M (3:1)$2.00$0.137
Cache read $/1M$0.10$0.0050
Cache write $/1M$1.25
Quality indices
Intelligence Index29.619.9
Coding Index43.9
Math Index83.7
Agentic Index16.4
Speed & latency
Output speed (tok/s)174
Time to first token85.85s
Time to first answer token85.85s
Benchmarks (Artificial Analysis)
MMLU-Pro78.0%
GPQA Diamond67.6%
Humanity's Last Exam8.2%
LiveCodeBench78.9%
SciCode36.6%
AIME 202583.7%
IFBench67.6%
AA-LCR (Long Context Reasoning)41.7%
Terminal-Bench Hard12.1%
τ²-Bench (Telecom)36.5%
Design Arena (Elo)
Website1,1491,129
UI components1,1421,109
Data viz1,1601,096
SVG1,072
3D1,1311,023
Game dev1,1551,104
Code categories1,1481,118
ASCII art1,182
Specs
Context window200K400K
Max output tokens64K128K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGPT