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 (batch)GPT-4.1 Mini
Claude Fable 5 (batch)

Anthropic

GPT-4.1 Mini

OpenAI

Pricing
Input $/1M$5.00$0.40
Output $/1M$25.00$1.60
Blended $/1M (3:1)$10.00$0.70
Cache read $/1M$0.50$0.10
Cache write $/1M$6.25
Quality indices
Intelligence Index49.610.2
Coding Index76.520.2
Math Index46.3
Agentic Index50.7
Speed & latency
Output speed (tok/s)620
Time to first token52.67s0s
Time to first answer token52.67s0s
Benchmarks (Artificial Analysis)
MMLU-Pro78.1%
GPQA Diamond92.6%66.4%
Humanity's Last Exam55.5%5.0%
LiveCodeBench48.3%
SciCode61.0%
MATH-50092.5%
AIME43.0%
AIME 202546.3%
IFBench63.5%38.3%
AA-LCR (Long Context Reasoning)82.3%44.0%
Terminal-Bench Hard62.9%7.6%
Terminal-Bench 2.184.6%10.1%
τ²-Bench (Telecom)98.5%52.9%
τ³-Bench Banking38.1%5.4%
Design Arena (Elo)
Website1,3091,010
Web apps1,274
Full-stack1,286
Mobile apps1,295
Android native1,293
UI components1,333976
Data viz1,3221,047
SVG1,329
3D1,347865
Game dev1,3591,094
Agentic game dev1,285
Godot game dev1,307
HTML slides1,280
Python→PPTX slides1,294
Agentic HTML slides1,254
Agentic slides (HTML)1,252
Code categories1,3251,009
ASCII art1,343
Specs
Context window1M1.05M
Max output tokens128K33K
Input modalitiestext, image, fileimage, text, file
TokenizerClaudeGPT