Alibaba
Qwen models for chat, vision, coding, and reasoning tasks.
Anthropic
Claude models with advanced reasoning, prompt caching, and extended thinking.
AWS Bedrock
Deploy models from major providers through AWS with enterprise security.
Azure
Azure OpenAI Service with enterprise features and Azure integration.
Bytedance
Bytedance’s language models and AI services platform.
Cerebras
Ultra-fast inference with Cerebras’ specialized AI chips.
Cohere
Cohere’s language models for text generation and understanding.
DeepSeek
DeepSeek’s advanced language models and reasoning capabilities.
ElevenLabs
Text-to-speech and voice synthesis with natural sounding audio.
Fal
Serverless GPU inference for generative AI models.
Google AI
Google’s AI models including Gemini and other services.
Google Vertex AI
Google Vertex AI platform for enterprise AI deployment.
Groq
Ultra-fast LLM inference with specialized hardware.
H Company
Mixture-of-Experts Holo3 models with vision and reasoning capabilities.
Inceptron
Leading open-source models via a high-performance, OpenAI-compatible inference API.
Jina
Multimodal embeddings and retrieval platform.
Leonardo AI
AI image generation and creative model suite.
LiteLLM
Unified proxy for custom or self-hosted LLM instances.
Mistral
Mistral’s open and efficient language models.
Moonshot AI
Chinese-optimized language models and AI services.
Nebius
Open-source models via Nebius Token Factory’s OpenAI-compatible API.
OpenAI
GPT models and OpenAI’s full suite of AI services.
OpenAI-compatible
Any OpenAI-compatible endpoint or custom deployment.
Perplexity
Perplexity AI’s research and language models.
Scaleway
Open-source models via Scaleway’s high-performance, OpenAI-compatible inference API.
Tensorix
Open-source models via a unified, OpenAI-compatible API.
Together AI
Open-source model serving and inference platform.
Wafer
Access GLM, Kimi, and Qwen models via Wafer Serverless infrastructure.
xAI
Grok chat and reasoning models from X.AI.
Z.ai
Specialized inference platform for optimized performance.