DeepInfra

Cloud PlatformOpenAI compatible

Serverless inference cloud for open-weight LLMs, image, video, TTS, transcription, embedding, and reranker models with an OpenAI-compatible API.

Active models
238
Families
75
Founded2022
API Base URL
Model
L3.1-70B-Euryale-v2.2๐ŸŒSao10K/L3.1-70B-Euryale-v2.2
L3.3-70B-Euryale-v2.3๐ŸŒSao10K/L3.3-70B-Euryale-v2.3
L3-8B-Lunaris-v1-Turbo๐ŸŒSao10K/L3-8B-Lunaris-v1-Turbo
GLM-5.2๐ŸŒOSSzai-org/GLM-5.2
GLM-5.1๐ŸŒOSSzai-org/GLM-5.1
GLM-5๐ŸŒOSSzai-org/GLM-5
GLM-4.7๐ŸŒOSSzai-org/GLM-4.7
GLM-4.7-Flash๐ŸŒOSSzai-org/GLM-4.7-Flash
GLM-4.6๐ŸŒOSSzai-org/GLM-4.6
Llama-4-Maverick-17B-128E-Instruct-FP8๐ŸŒOSSmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8