New feature: Added support for fine-tuning open-weight models using OpenAI-compatible APIs. You can now create, monitor, and manage reinforcement fine-tuning jobs for open-weight models through familiar OpenAI SDK endpoints, including Files API, fine-tunin

Fine-tune open-weight models using OpenAI-compatible APIs

Amazon Bedrock provides OpenAI compatible API endpoints for fine-tuning foundation models. These endpoints allow you to use familiar OpenAI SDKs and tools to create, monitor, and manage fine-tuning jobs with Amazon Bedrock models.

Key capabilities

• Upload training files
• Create fine-tuning jobs
• List and retrieve jobs
• Monitor job events
• Access checkpoints
• Immediate inference
• Easy migration

Reinforcement fine-tuning workflow for open-weight models

1. Upload Training Dataset
2. Configure Reward Function
3. Create Fine-tuning Job
4. Monitor Training Progress
5. Run Inference

Supported regions and endpoints

• OpenAI
• Model: Gpt-oss-20B
• Model ID: openai.gpt-oss-20b
• Region: US West (Oregon)
• Endpoint: bedrock-mantle.us-west-2.api.aws
• Qwen
• Model: Qwen3 32B
• Model ID: qwen.qwen3-32b
• Region: US West (Oregon)
• Endpoint: bedrock-mantle.us-west-2.api.aws

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.