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
Claude Haiku 4.5

Anthropic

DeepSeek V4 Flash

DeepSeek

Pricing
Input $/1M$1.00$0.094
Output $/1M$5.00$0.188
Blended $/1M (3:1)$2.00$0.117
Cache read $/1M$0.10$0.019
Cache write $/1M$1.25
Quality indices
Intelligence Index29.640.3
Coding Index43.956.2
Math Index
Agentic Index16.431.1
Speed & latency
Output speed (tok/s)113
Time to first token0.85s
Time to first answer token50.40s
Benchmarks (Artificial Analysis)
GPQA Diamond89.4%
Humanity's Last Exam32.1%
SciCode44.9%
IFBench79.2%
AA-LCR (Long Context Reasoning)63.0%
Terminal-Bench Hard35.6%
Terminal-Bench 2.161.8%
τ²-Bench (Telecom)95.0%
τ³-Bench Banking22.9%
Design Arena (Elo)
Website1,1491,235
UI components1,1421,205
Data viz1,1601,159
SVG1,0721,202
3D1,1311,248
Game dev1,1551,254
Code categories1,1481,239
ASCII art1,1821,157
Specs
Context window200K1.05M
Max output tokens64K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek