tencent cloud

Supported Models

Download
Focus Mode
Font Size
Last updated: 2026-11-17 14:27:52
AI-Translated & Reviewed

Overview

Model providers serve as the bridge between CMR and the specific models that users actually invoke. The BYOK (Bring Your Own Key) mode allows users to bring their own model keys and flexibly connect to original vendor models, third-party proxies, or self-built models. Through CMR, users can flexibly choose different invocation channels and model providers to meet diverse AI application requirements.

Supported Provider Types

Provider Type
Description
Resource Consumption
Status
BYOK original vendor model provider
Call models from the original AI platform provider through CMR
Consumes the user's tokens on the original AI platform or computing platform
Online
BYOK third-party proxy provider
Call models on third-party AI platforms through CMR
Consumes the user's tokens on a third-party AI platform
Online
BYOK self-built model provider
Call user-privately-deployed models through CMR
Consumes the user's own tokens on the self-built AI platform
Online

Preset Model Providers and Models in BYOK Mode

Attention:
Preset models may not be updated in a timely manner due to vendor adjustments. If you cannot find the model name you expect, you can configure the URL and model name through a BYOK third-party proxy provider.
Model Provider
Model
DeepSeek
deepseek-chat
deepseek-reasoner
Alibaba Cloud Bailian
Qwen3.6-Plus
Qwen3.5-Plus
Qwen3.5-Flash
Qwen3-Max
Qwen3-VL-Plus
Qwen3-VL-Flash
Zhipu AI
GLM-5
GLM-5-Turbo
GLM-4.7
GLM-4.7-FlashX
GLM-4.6
GLM-4.5
GLM-4.5-Air
GLM-4.7-Flash
Moonshot AI
kimi-k2.5
moonshot-v1-8k-preview
moonshot-v1-8k
kimi-k2-thinking
moonshot-v1-auto
moonshot-v1-32k-preview
kimi-k2-turbo-preview
kimi-k2-0711-preview
kimi-k2-0905-preview
kimi-k2-thinking-turbo
moonshot-v1-32k
moonshot-v1-128k
kimi-latest
moonshot-v1-128k-preview
MiniMax
MiniMax-M2.7
MiniMax-M2.7-highspeed
MiniMax-M2.5
MiniMax-M2.5-highspeed
MiniMax-M2.1
MiniMax-M2.1-highspeed
MiniMax-M2
Volcano Engine
doubao-seed-2-0-pro-260215
doubao-seed-2-0-lite-260215
doubao-seed-2-0-mini-260215
doubao-seed-2-0-code-preview-260215
Tencent Cloud TokenHub
hy3
hy3-preview
hy-mt2-pro
hy-mt2-plus
hy-mt2-lite
hunyuan-role-latest
hy-role
deepseek-v4-flash-202605
deepseek-v4-pro-202606
deepseek-v4-flash
deepseek-v4-pro
deepseek-v3.2
glm-5.2
glm-5.1
glm-5v-turbo
glm-5-turbo
glm-5
kimi-k2.7-code-highspeed
kimi-k3
kimi-k2.7-code
kimi-k2.6
kimi-k2.5
minimax-m3
minimax-m2.7
minimax-m2.5
qwen3.5-flash
qwen3.5-plus
hy-image-v3.0
hy-image-lite
hy-video-1.5
yt-video-2.0
yt-video-humanactor
yt-video-fx
kl-video-v3
kl-video-v2-6
kl-video-v2-5-turbo
kl-video-v2-1-master
kl-video-v2-1
kl-video-v2-master
kl-video-v1-6
kl-video-v1-5
kl-video-v1
vd-video-q3-pro
vd-video-q3-turbo
vd-video-q2-pro
vd-video-q2-pro-fast
vd-video-q2-turbo
vd-video-q2
hy-3d-3.0
hy-3d-3.1
hy-3d-express
youtu-vita
hy-vision-2.0-instruct
hunyuan-t1-vision-20250916
hunyuan-turbos-vision-video-20250728
kinfra-text-embedding-0.6b
kinfra-text-embedding-4b
kinfra-vl-embedding-2b
kinfra-vl-embedding-8b

Best Practice Recommendations

For scenarios with high stability and reliability requirements, it is recommended to use a BYOK original vendor model provider.
For scenarios that require flexibility and customization, it is recommended to use a BYOK third-party proxy provider or a BYOK self-built model provider.



Help and Support

Was this page helpful?

Help us improve! Rate your documentation experience in 5 mins.

Feedback