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 Fable 5.1GPT-5.6 Terra
Claude Fable 5.1

Anthropic

GPT-5.6 Terra

OpenAI

Pricing
Input $/1M$10.00$2.00
Output $/1M$50.00$12.00
Blended $/1M (3:1)$20.00$4.50
Cache read $/1M$0.25$0.20
Cache write $/1M$12.50$2.50
Quality indices
Intelligence Index53.442.1
Coding Index81.676.7
Math Index
Agentic Index57.943.2
Speed & latency
Output speed (tok/s)7388
Time to first token153.32s130.06s
Time to first answer token153.32s130.06s
Benchmarks (Artificial Analysis)
GPQA Diamond93.7%92.5%
Humanity's Last Exam59.1%42.9%
SciCode63.1%55.0%
IFBench71.2%
AA-LCR (Long Context Reasoning)85.3%83.0%
Terminal-Bench Hard57.6%
Terminal-Bench 2.191.4%88.0%
τ²-Bench (Telecom)86.3%
τ³-Bench Banking47.2%40.2%
Design Arena (Elo)
Website1,323
Web apps1,336
Full-stack1,336
UI components1,336
Data viz1,369
SVG1,347
3D1,425
Game dev1,404
Python→PPTX slides1,328
Code categories1,346
ASCII art1,330
Specs
Context window1M1.05M
Max output tokens128K128K
Input modalitiestext, image, filefile, image, text
TokenizerClaudeGPT