AI Providers

NovitaAI's OpenAI-compatible large language models

Alibaba Cloud's Qwen large language models with OpenAI-compatible API

OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits all of humanity.

Google AI Studio is a platform for accessing Google's Gemini models.

Microsoft Azure - enterprise-grade OpenAI models

Google Vertex AI is a platform for accessing Google's Gemini models via Vertex AI.

Nebius AI Studio - OpenAI-compatible API for large language models

Anthropic is a research and deployment company focused on building safe and useful AI.

xAI's Grok large language models

Amazon Bedrock - fully managed service for foundation models

Z AI's OpenAI-compatible large language models

CanopyWave is a platform for running large language models with OpenAI-compatible API

ByteDance's ModelArk platform with OpenAI-compatible API for large language models

Weights & Biases Inference (powered by CoreWeave) provides OpenAI-compatible inference for open-weight models — including DeepSeek V4 Flash, DeepSeek R1, Llama, and Qwen — at very competitive prices.

Mistral AI's large language models

Together AI is a platform for running large language models in the cloud with fast inference.

MiniMax's large language models with advanced reasoning and coding capabilities

EmberCloud provides access to a variety of large language models via an OpenAI-compatible API

DeepInfra provides OpenAI-compatible inference for a wide catalog of open-weight models (Llama, DeepSeek, GLM, Qwen, etc.).

Cerebras high-performance inference with ultra-fast throughput

Groq's ultra-fast LPU inference with various models

Moonshot AI's OpenAI-compatible large language models

Avalanche - video generation provider.

GMI Cloud provides OpenAI-compatible serverless inference for open-weight and frontier models on NVIDIA GPU infrastructure.

Glacier is a stealth provider with Google AI Studio-compatible Gemini endpoints.

Quartz is a Vertex-compatible provider for accessing Gemini and other Vertex-routed models.

Perplexity's AI models for search and conversation with real-time web access

Bitdeer AI Model Studio provides OpenAI-compatible serverless inference for open-weight models including DeepSeek V4 Flash.

Inference.net is a platform for running large language models in the cloud.

NanoGPT offers a large selection of models

DeepSeek's high-performance language models with OpenAI-compatible API

Bluestone's OpenAI-compatible LLM inference API

Fireworks AI serves open-weight models (including MiniMax) with fast, OpenAI-compatible inference.

Parasail provides serverless OpenAI-compatible inference for open-weight models including Kimi K2.