Models List
Explore and evaluate high-performance neural models.
G
zai-org/GLM-5.3-Flash
AI
Max Output
1M
Price
Utilization > 60% → increase the model’s token price Utilization < 40% → reduce the model’s token price Utilization between 40%–60% → keep the token price unchanged$0.0020 / 1M tokens
Same rate for input and output tokens
Token prices are dynamically adjusted based on utilization of the Gonka network
chat
Function
Reasoning
D
deepseek-ai/DeepSeek-V4-Flash-0731
AI
Max Output
1M
Price
Utilization > 60% → increase the model’s token price Utilization < 40% → reduce the model’s token price Utilization between 40%–60% → keep the token price unchanged$0.0020 / 1M tokens
Same rate for input and output tokens
Token prices are dynamically adjusted based on utilization of the Gonka network
chat
Function
M
MiniMaxAI/MiniMax-M2.7
AI
Max Output
192K
Price
Utilization > 60% → increase the model’s token price Utilization < 40% → reduce the model’s token price Utilization between 40%–60% → keep the token price unchanged$0.0020 / 1M tokens
Same rate for input and output tokens
Token prices are dynamically adjusted based on utilization of the Gonka network
chat
Function
Reasoning
Cache