Deploy Dedicated GPU server to run AI models
Explore our collection of pre-built AI workflows for various use cases
Create custom AI workflows tailored to your specific needs
API details in LLM-friendly format
Command-line interface for API
Skills for coding agents to use APIs
Agents Control Plane for API
SDKs for ModelsLab API
MCP Server for API
openai-gpt-5.4-mini
2001 API Calls
mistralai-mistral-small-2603
2000 API Calls
openai-gpt-5.4-nano
minimax-minimax-m2.5-free
z-ai-glm-5-turbo
2011 API Calls
x-ai-grok-4.20-beta
2039 API Calls
x-ai-grok-4.20-multi-agent-beta
2004 API Calls
openrouter-hunter-alpha
2019 API Calls
openrouter-healer-alpha
2003 API Calls
nvidia-nemotron-3-super-120b-a12b-free
2014 API Calls
qwen-qwen3.5-9b
bytedance-seed-seed-2.0-lite
openai-gpt-5.4-pro
2042 API Calls
inception-mercury-2
openai-gpt-5.4
2056 API Calls
openai-gpt-5.3-chat
2006 API Calls
google-gemini-3.1-flash-lite-preview
2236 API Calls
upstage-solar-pro-3
2008 API Calls
qwen-qwen3.5-35b-a3b
qwen-qwen3.5-27b