Model Library
We provide top-tier open-source models of various types and support your
diverse deployment needs for flexible, high-performance AI applications
We provide top-tier open-source models of various types and support your diverse deployment needs for flexible, high-performance AI applications
All Models
VISION
MiMo-V2.5
311B
1M context
Learn more
CHAT
Deepseek-V4-Flash
284B
1M context
Learn more
VISION
Kimi K2.6
1T
256K context
Learn more
CODE
GLM 5.1
754B
200K context
Learn more
CODE
MiniMax M2.5
205K context
Learn more
CHAT
MiMo-V2-Flash
310B
256K context
Learn more
Which deployment fits your needs
Serverless Endpoints
Canopy Wave gives you instant access to the most popular OSS models — optimized for cost, speed, and quality on the fastest AI cloud.
Simplest setup
Highest flexibility
Provide popular models on the market
Pay per token
Dedicated Endpoints
Canopy Wave allows you to create on-demand deployments of GPU cluster that are reserved for your own use.
No hard rate limits
Predictable performance
Custom large models can be deployed.
Pay for GPU runtime
Serverless Endpoints
Canopy Wave gives you instant access to the most popular OSS models — optimized for cost, speed, and quality on the fastest AI cloud.
Dedicated Endpoints
Canopy Wave allows you to create on-demand deployments of GPU cluster that are reserved for your own use.
Simplest setup
No hard rate limits
Highest flexibility
Predictable performance
Provide popular models on the market
Custom large models can be deployed.
Pay per token
Pay for GPU runtime