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 V4 Flash 0423
Claude Haiku 4.5

Anthropic

DeepSeek V4 Flash 0423

DeepSeek

Pricing
Input $/1M$1.00$0.037
Output $/1M$5.00$0.074
Blended $/1M (3:1)$2.00$0.047
Cache read $/1M$0.10$0.0074
Cache write $/1M$1.25
Quality indices
Intelligence Index16.934.3
Coding Index43.969.1
Math Index
Agentic Index822.2
Speed & latency
Output speed (tok/s)241
Time to first token0.98s
Time to first answer token9.28s
Benchmarks (Artificial Analysis)
GPQA Diamond90.8%
Humanity's Last Exam38.6%
SciCode50.3%
AA-LCR (Long Context Reasoning)79.7%
Terminal-Bench 2.178.7%
τ³-Bench Banking39.4%
Design Arena (Elo)
Website1,1351,220
UI components1,1151,180
Data viz1,1391,142
SVG1,0491,179
3D1,1011,217
Game dev1,1201,220
Code categories1,1301,220
ASCII art1,1591,129
Specs
Context window200K1.05M
Max output tokens64K384K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek