Model Library

Browse our supported open source models

Large Language Models

Newmeta-llama/llama-4-maverick-17b-128e-instruct-fp8Llama 4 Maverick InstructLLM$0.17/0.85 in/out MTokens | 1048576 Context
Newmeta-llama/llama-4-scout-17b-16e-instructLlama 4 Scout InstructLLM$0.1/0.5 in/out MTokens | 131072 Context
Newdeepseek/deepseek-v3-0324DeepSeek V3 0324LLM$0.33/1.3 in/out MTokens | 128000 Context
Newqwen/qwen2.5-vl-72b-instructQwen:Qwen2.5-vl-72b-instructLLM$0.8/0.8 in/out MTokens | 96000 Context
Newdeepseek/deepseek-v3-turboDeepSeek V3 (Turbo) LLM$0.4/1.3 in/out MTokens | 64000 Context
60% OFFdeepseek/deepseek-r1-turboDeepSeek R1 (Turbo) LLM$0.7/2.5 in/out MTokens | 64000 Context
Newgoogle/gemma-3-27b-itGemma 3 27BLLM$0.119/0.2 in/out MTokens | 32000 Context
qwen/qwq-32bQwen: QwQ 32BLLM$0.18/0.2 in/out MTokens | 32768 Context
See All

Embedding Models

NewBBAAI:BGE-M3Embedding$0.01 in MTokens | 8192 Context

Image Models

Stable Diffusion 1.5Stable Diffusion 1.5Text to ImageImage to Image$0.003 / Image | 1024*1024 20steps
Stable Diffusion XLStable Diffusion XLText to ImageImage to Image$0.003 / Image | 1024*1024 20steps
FLUX.1 [schnell]FLUX.1 [schnell]Text to Image$0.003 / Image | 1024*1024 4steps

Audio Models

TTTS ModelText to Speech$15 / 1M characters

Video Models

NewWan 2.1 T2VWan 2.1 T2VText to Video$0.08/s (1280*720)
Wan 2.1 I2VWan 2.1 I2VImage to Video$0.08/s (1280*720)
HHunyuan Video FastText to Video$0.18/s (1280*720 24fps)
AnimateDiffAnimateDiffText to Video$0.0307/video | 32 total frames 20steps
Stable Video DiffusionStable Video DiffusionImage to Video$0.0134/video | 20steps

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