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 Terminus
Claude Haiku 4.5

Anthropic

DeepSeek V3.1 Terminus

DeepSeek

Pricing
Input $/1M$1.00$0.27
Output $/1M$5.00$1.00
Blended $/1M (3:1)$2.00$0.453
Cache read $/1M$0.10$0.135
Cache write $/1M$1.25
Quality indices
Intelligence Index16.913.9
Coding Index43.943.5
Math Index53.7
Agentic Index86.8
Speed & latency
Output speed (tok/s)0
Time to first token0s
Time to first answer token0s
Benchmarks (Artificial Analysis)
MMLU-Pro83.6%
GPQA Diamond75.1%
Humanity's Last Exam8.7%
LiveCodeBench52.9%
AIME 202553.7%
IFBench41.2%
AA-LCR (Long Context Reasoning)45.3%
Terminal-Bench Hard31.8%
τ²-Bench (Telecom)37.1%
Design Arena (Elo)
Website1,1351,199
UI components1,1151,198
Data viz1,1391,183
SVG1,0491,088
3D1,1011,169
Game dev1,1201,154
Code categories1,1301,190
ASCII art1,159
Specs
Context window200K164K
Max output tokens64K33K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek