Llama 4 Scout & Maverick models are now available. Try them!
Models
Docs
Pricing
Chat
DeepStart
Blog
Documentation
GPU Instances
Contents
GPU Instances provide on-demand access to high-performance GPU compute resources in the cloud:
Latest Models
Gryphe/
MythoMax-L2-13b
Phind/
Phind-CodeLlama-34B-v2
openai/
whisper-tiny
bigcode/
starcoder2-15b
openchat/
openchat_3.5
Featured Models
deepseek-ai/
DeepSeek-Prover-V2-671B
meta-llama/
Llama-4-Scout-17B-16E-Instruct
Llama-3.3-70B-Instruct
mistralai/
Mistral-Small-3.1-24B-Instruct-2503
DeepSeek-R1-Distill-Llama-70B
microsoft/
phi-4-reasoning-plus
Company
Compare
About
Careers
Trust Center
Privacy
Terms
© 2025 Deep Infra. All rights reserved.