Coding Plan is now lCoding Plan is now live! Explore nowDeepSeek V3.1
Mobile Banner 7

Coding Plan

The Best Coding Plan for Open Models.

Mobile Banner 5

Kimi K2.5
is live on Canopy Wave

Mobile Banner 4

GLM-5 Launches on Canopy Wave

Mobile Banner 6

MiniMax M2.5
Launches on Canopy Wave

Best AI Inference Platform for Open Models

Moonshot AI
Zhipu AI
DeepSeek
Qwen
MiniMax
Xiaomi MiMo
Model Library

Advanced. Secure. Fast
Open Models Now Available

You can enjoy a quick experience via chat, or access them easily through API integration.

New
VISION
Kimi-K2.5 logo
Kimi-K2.5
$0.50
Input
$2.80
Output
$0.10
Cache
256K
Context
New
CODE
GLM-5 logo
GLM-5
$0.90
Input
$3.10
Output
$0.20
Cache
200K
Context
New
CODE
MiniMax-M2.5 logo
MiniMax-M2.5
$0.27
Input
$1.08
Output
$0.03
Cache
205K
Context
CHAT
DeepSeek-V3.2 logo
DeepSeek-V3.2
$0.26
Input
$0.40
Output
$0.052
Cache
163.8K
Context
CHAT
MiMo-V2-Flash logo
MiMo-V2-Flash
$0.08
Input
$0.24
Output
$0.04
Cache
256K
Context
Serverless Inference

Easy access via simple APIs

No need to deploy or manage the AI infrastructure

Coding Plan

The Best Coding Plan for Open Models

A package with multiple models designed exclusively for developers

How to Use Canopy Wave API

Integrate Tools with Canopy Wave API

We provide OpenAI-compatible APIs that you can integrate into various tools.

Sign up for free credits, enough to build a real AI project.

ClineClineCline
Roo CodeRoo CodeRoo Code
Kilo CodeKilo CodeKilo Code
DifyDifyDify
OpenClawOpenClawOpenClaw
Open CodeOpen CodeOpen Code
Silly TavernSilly TavernSilly Tavern
Open WebUIOpen WebUIOpen WebUI
Cherry StudioCherry StudioCherry Studio
ChatboxChatboxChatbox
Why Choose Canopy Wave

Best AI Inference Platform for Open Models

Open Community

Open Community

Designed to support advanced, secure, and fast open models.

High Quality

High Quality

Powered by cutting-edge GPUs and optimized inference pipelines for fast, reliable production workloads.

Enterprise-Grade Trust

Enterprise-Grade Trust

Models are hosted in our private cloud with full data isolation, zero data retention and no training usage.

Full operational and security control

Full operational and security control​

In-house clusters with real-time monitoring, diagnostics, and alerts to ensure GPU health, high SLA and utilization.

Full AI Stack

Full AI Stack

From AI infrastructure to end-to-end AI services, we help enterprises move faster, operate smarter, and scale more efficiently.

Partners Powering Our Growth

Moonshot AI
Zhipu AI
DeepSeek
Qwen
MiniMax
Xiaomi MiMo
Partner 14
Partner 15
Partner 16
Partner 17
Partner 18
Partner 19
Brand 1
Brand 2
Brand 3
Brand 4
Brand 5
Brand 6
Brand 7
Brand 8
Brand 9
Brand 11
Brand 12
Brand 13
Brand 14
Brand 15
Brand 16
Partner 14
Partner 15
Partner 16
Partner 17
Partner 18
Partner 19
Brand 1
Brand 2
Brand 3
Brand 4
Brand 5
Brand 6
Brand 7
Brand 8
Brand 9
Brand 11
Brand 12
Brand 13
Brand 14
Brand 15
Brand 16

Accelerate Your AI Journey today

PromotionContact us