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 4.5DeepSeek V3.1
Claude Haiku 4.5

Anthropic

DeepSeek V3.1

DeepSeek

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$0.95
Blended $/1M (3:1)$2.00$0.425
Cache read $/1M$0.10$0.13
Cache write $/1M$1.25
Quality indices
Intelligence Index29.621
Coding Index43.9
Math Index49.7
Agentic Index16.4
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
MMLU-Pro83.3%
GPQA Diamond73.5%
Humanity's Last Exam6.3%
LiveCodeBench57.7%
SciCode36.7%
AIME 202549.7%
IFBench37.8%
AA-LCR (Long Context Reasoning)45.0%
Terminal-Bench Hard24.2%
τ²-Bench (Telecom)34.8%
Design Arena (Elo)
Website1,1491,150
UI components1,1421,126
Data viz1,1601,136
SVG1,0721,014
3D1,1311,136
Game dev1,1551,143
Code categories1,1481,145
ASCII art1,182
Specs
Context window200K164K
Max output tokens64K33K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek