Documentation Index
Fetch the complete documentation index at: https://docs.wandb.ai/llms.txt
Use this file to discover all available pages before exploring further.
The Serverless RL API provides endpoints for managing training jobs, including serverless reinforcement learning (RL) and supervised fine-tuning (SFT). The API is OpenAI-compatible for chat completions.
Authentication
All API requests require authentication using your W&B API key. Create an API key at wandb.ai/settings. Include your API key in theAuthorization header:
Base URL
Available endpoints
The following sections describe the available endpoints, grouped by resource type.Chat completions
- POST /v1/chat/completions - Create Chat Completion
- POST /v1/chat/completions/ - Create Chat Completion
Models
- POST /v1/preview/models - Create Model
- DELETE /v1/preview/models/ - Delete Model
- DELETE /v1/preview/models//checkpoints - Delete Model Checkpoints
- GET /v1/preview/models//checkpoints - List Model Checkpoints
- POST /v1/preview/models//log - Log
Training jobs
- POST /v1/preview/sft-training-jobs - Create Sft Training Job
- POST /v1/preview/training-jobs - Create Rl Training Job
- GET /v1/preview/training-jobs/ - Get Training Job
- GET /v1/preview/training-jobs//events - Get Training Job Events
Health
- GET /v1/health - Health Check
- GET /v1/system-check - System Check