Model Comparison
Kimi-K2-Instruct
vs
Qwen3-235B-A22B-Instruct-2507
Jan 13, 2026
Pricing
Input
$
0.58
/ M Tokens
$
0.09
/ M Tokens
Output
$
2.29
/ M Tokens
$
0.6
/ M Tokens
Metadata
Create on
Jul 11, 2025
Jul 21, 2025
License
-
APACHE-2.0
Provider
Moonshot AI
Qwen
Specification
State
Available
Available
Architecture
Calibrated
No
Yes
Mixture of Experts
Yes
Yes
Total Parameters
1000B
235B
Activated Parameters
32B
22B
Reasoning
No
No
Precision
FP8
FP8
Context length
131K
262K
Max Tokens
131K
262K
Supported Functionality
Serverless
Supported
Supported
Serverless LoRA
Not supported
Not supported
Fine-tuning
Not supported
Not supported
Embeddings
Not supported
Not supported
Rerankers
Not supported
Not supported
Support image input
Not supported
Not supported
JSON Mode
Supported
Supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Supported
Kimi-K2-Instruct in Comparison
See how Kimi-K2-Instruct compares with other popular models across key dimensions.
