Free Inference
Getting Started:
Quick Start
Step 1: Get Your API Key
Step 2: Choose Your IDE
Cursor
Codex
Roo Code / Kilo Code
Step 3: Choose a Model
Next Steps
Need Help?
IDE & Coding Agent Integrations
Codex
Configuration Steps
Cursor
Configuration Steps
Roo Code & Kilo Code
Configuration Steps
Codebase Indexing
Roo Code
Kilo Code
Alternative: Local Qdrant
Using the Embedding API Directly
Troubleshooting
Connection Issues
Model Not Found
Codex-Specific Issues
Cursor-Specific Issues
Roo Code / Kilo Code Issues
Need Help?
Available Models
Model Overview
Embedding Models
Model Details
GLM-5
GLM-4.7
GLM-4.7-Flash
MiniMax M2.5
MiniMax M2
Qwen3 Coder 30B
Llama 3.3 70B Instruct (Limited Capacity)
Llama 4 Scout (Limited Capacity)
Llama 4 Maverick (Limited Capacity)
BGE-M3 (Embedding)
Switching Models
Free Inference
Index
Index