Model Library
Browse our supported open source models
Large Language Models
New
Llama 4 Maverick Instruct$0.17/0.85 in/out MTokens | 1048576 Context
Llama 4 Maverick Instruct$0.17/0.85 in/out MTokens | 1048576 ContextNewLlama 4 Scout Instruct$0.1/0.5 in/out MTokens | 131072 Context
Llama 4 Scout Instruct$0.1/0.5 in/out MTokens | 131072 ContextNew
DeepSeek V3 0324$0.33/1.3 in/out MTokens | 128000 Context
DeepSeek V3 0324$0.33/1.3 in/out MTokens | 128000 ContextNew
Qwen:Qwen2.5-vl-72b-instruct$0.8/0.8 in/out MTokens | 96000 Context
Qwen:Qwen2.5-vl-72b-instruct$0.8/0.8 in/out MTokens | 96000 ContextNewDeepSeek V3 (Turbo) $0.4/1.3 in/out MTokens | 64000 Context
DeepSeek V3 (Turbo) $0.4/1.3 in/out MTokens | 64000 ContextDeepSeek R1 (Turbo) $0.7/2.5 in/out MTokens | 64000 ContextNew
Gemma 3 27B$0.119/0.2 in/out MTokens | 32000 Context
Gemma 3 27B$0.119/0.2 in/out MTokens | 32000 ContextQwen: QwQ 32B$0.18/0.2 in/out MTokens | 32768 ContextEmbedding Models
NewBBAAI：BGE-M3$0.01 in MTokens | 8192 Context
Image Models
Stable Diffusion 1.5$0.003 / Image | 1024*1024 20stepsStable Diffusion XL$0.003 / Image | 1024*1024 20steps![FLUX.1 [schnell]](/_next/image?url=%2Fmodels%2Flogo%2Fflux-logo.png&w=64&q=75){kind=logo}
FLUX.1 [schnell]$0.003 / Image | 1024*1024 4stepsAudio Models
TTTS Model$15 / 1M characters
Video Models
NewWan 2.1 T2V$0.08/s (1280*720)
Wan 2.1 T2V$0.08/s (1280*720)Wan 2.1 I2V$0.08/s (1280*720)HHunyuan Video Fast$0.18/s (1280*720 24fps)
AnimateDiff$0.0307/video | 32 total frames 20stepsStable Video Diffusion$0.0134/video | 20steps
Ready to build smarter? Start today.
Get started with Novita AI and unlock the power of affordable, reliable, and scalable AI inference for your applications.
Building an AI startup? Get up to $10,000 in credits!
Get up to $10,000 in credits and dedicated support to grow and scale your AI startup.
Apply Now