HyperAI
Command Palette
Search for a command to run...
LLM Model Comparison
Compare LLM model specifications and capabilities side by side
kimi-k2-thinking
weaver
mancer
Modalities
Modalities
Specifications
Specifications
Context Length
131,072
Context Length
8,000
Max Output Tokens
65,535
Max Output Tokens
2,000
Release Date
11/6/2025
Release Date
8/2/2023
Pricing
Pricing
Input Price ($/M tokens)
37.3% cheaper
$0.47
Input Price ($/M tokens)
$0.75
Output Price ($/M tokens)
$2.00
Output Price ($/M tokens)
50.0% cheaper
$1.00
Capabilities
Capabilities
Reasoning
Reasoning
Tool Calling
Tool Calling
Structured Outputs
Structured Outputs
Web Search
Web Search
Benchmarks
Benchmarks
swe-bench (Verified)
63.4%
swe-bench (Verified)
-
swe-bench (bash-only)
63.4%
swe-bench (bash-only)
-