GLM 4.5 is on Novita!
Don't show again

Model Library

Browse our supported open source models

Large Language Models

Browse our supported open source models and deploy in dedicated endpoints

Hot
deepseek/deepseek-v3-0324DeepSeek V3 0324Chat$0.28/1.14 in/out MTokens | 163840 Context
New
qwen/qwen3-235b-a22b-thinking-2507Qwen3 235B A22b Thinking 2507Chat$0.3/3 in/out MTokens | 131072 Context
New
MKimi K2 InstructChat$0.57/2.3 in/out MTokens | 131072 Context
New
qwen/qwen3-coder-480b-a35b-instructQwen3 Coder 480B A35B InstructChat$0.64/2.5 in/out MTokens | 262144 Context
New
ZGLM-4.5Chat$0.6/2.2 in/out MTokens | 131072 Context
deepseek/deepseek-r1-0528DeepSeek R1 0528Chat$0.7/2.5 in/out MTokens | 163840 Context
New
qwen/qwen3-235b-a22b-instruct-2507Qwen3 235B A22B Instruct 2507Chat$0.15/0.8 in/out MTokens | 262144 Context
BERNIE 4.5 VL 424B A47BChat$0.42/1.25 in/out MTokens | 123000 Context
BERNIE 4.5 300B A47BChat$0.28/1.1 in/out MTokens | 123000 Context
qwen/qwen3-30b-a3b-fp8Qwen3 30B A3BChat$0.1/0.45 in/out MTokens | 40960 Context
New
minimaxai/minimax-m1-80kMiniMax M1Chat$0.55/2.2 in/out MTokens | 1000000 Context
Dedicated
deepseek/deepseek-r1-0528-qwen3-8bDeepSeek R1 0528 Qwen3 8BChat$0.06/0.09 in/out MTokens | 128000 Context
qwen/qwen3-32b-fp8Qwen3 32BChat$0.1/0.45 in/out MTokens | 40960 Context
qwen/qwen2.5-vl-72b-instructQwen2.5 VL 72B InstructChat$0.8/0.8 in/out MTokens | 32768 Context
See All

Embedding Models

New
qwen/qwen3-embedding-8bQwen3 Embedding 8BEmbedding$0.05 in MTokens | 32768 Context
Free
BBAAI:BGE-M3Embedding$0 in MTokens | 8192 Context

Video Models

New
MiniMax Hailuo 02MiniMax Hailuo 02Image to VideoText to Video$0.44/video 1080P 6s
KKling V1.6 Text to VideoText to Video$0.27/video 720P 5s
KKling V1.6 Image to VideoImage to Video$0.46/video 1080P Pro 5s
MiniMax Video 01MiniMax Video 01Image to VideoText to Video$0.40/video 720P 6s
Wan 2.1 Text to VideoWan 2.1 Text to VideoText to Video$0.30/video (1280*720) 5s
Wan 2.1 Image to VideoWan 2.1 Image to VideoImage to Video$0.30/video (1280*720) 5s
HHunyuan Video FastText to Video$0.30/video (1280*720) 5s

Audio Models

New
MiniMax speech-02-hdMiniMax speech-02-hdText to Speech$80 / 1M characters
New
MiniMax speech-02-turboMiniMax speech-02-turboText to Speech$48 / 1M characters

Image Models

SSeedream 3.0 Text to ImageText to Image$0.03/image

Dedicated Endpoint

Enterprise-Grade Infrastructure for AI

For enterprises that require higher performance, tailored SLAs, or private hosting for custom models
  • Custom pricing
  • Guaranteed uptime & latency
  • Unlimited scale
  • Dedicated clusters
Get Enterprise-Grade Endpoint
de-banner