Model Comparison
ERNIE-4.5-300B-A47B
vs
Kimi-K2-Instruct-0905
Feb 28, 2026
Pricing
Input
$
0.28
/ M Tokens
$
0.4
/ M Tokens
Output
$
1.1
/ M Tokens
$
2.0
/ M Tokens
Metadata
Create on
Sep 3, 2025
License
MODIFIED MIT LICENSE
Provider
BAIDU
Moonshot AI
Specification
State
Available
Available
Architecture
Mixture-of-Experts
Mixture-of-Experts (MoE)
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
300B
1000B
Activated Parameters
47B
32B
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
Not supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Not supported
ERNIE-4.5-300B-A47B in Comparison
See how ERNIE-4.5-300B-A47B compares with other popular models across key dimensions.
VS
MiniMax-M2.5
VS
GLM-5
VS
Step-3.5-Flash
VS
GLM-4.7
VS
MiniMax-M2.1
VS
GLM-4.6V
VS
Kimi-K2-Thinking
VS
MiniMax-M2
VS
GLM-4.6
VS
Qwen3-VL-235B-A22B-Instruct
VS
Qwen3-VL-235B-A22B-Thinking
VS
Ring-flash-2.0
VS
Ling-flash-2.0
VS
Qwen3-Next-80B-A3B-Instruct
VS
Qwen3-Next-80B-A3B-Thinking
VS
Kimi-K2-Instruct-0905
VS
GLM-4.5V
VS
gpt-oss-120b
VS
step3
VS
Qwen3-235B-A22B-Thinking-2507
