Skip to content

Conversation

@anatolyburtsev
Copy link
Contributor

Summary

This PR adds support for OpenAI's new open-weight GPT-OSS models that are now available on AWS Bedrock.

Pricing is based on https://aws.amazon.com/bedrock/pricing/

Note

only available in us-west-2 region

Testing

Tested by configuring MODEL_LIST_CONFIG_JSON to local models.json.

Screenshot 2025-08-21 at 4 40 59 PM

No idea why it pretends to be gpt-4, but it works.

Screenshot 2025-08-21 at 4 41 04 PM

- Add openai.gpt-oss-20b-1:0 (21B parameters, optimized for lower latency)
- Add openai.gpt-oss-120b-1:0 (120B parameters, optimized for production use)
- gpt-oss-20b: /bin/zsh.07//bin/zsh.30 per 1M tokens (input/output)
- gpt-oss-120b: /bin/zsh.15//bin/zsh.60 per 1M tokens (input/output)
Copy link
Contributor

@HenryHengZJ HenryHengZJ left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

@HenryHengZJ HenryHengZJ merged commit a5a728f into FlowiseAI:main Aug 31, 2025
2 checks passed
erhhung pushed a commit to erhhung/flowise that referenced this pull request Oct 5, 2025
* feat: add OpenAI GPT-OSS models to AWS Bedrock

- Add openai.gpt-oss-20b-1:0 (21B parameters, optimized for lower latency)
- Add openai.gpt-oss-120b-1:0 (120B parameters, optimized for production use)

* fix: update GPT-OSS models pricing on AWS Bedrock

- gpt-oss-20b: /bin/zsh.07//bin/zsh.30 per 1M tokens (input/output)
- gpt-oss-120b: /bin/zsh.15//bin/zsh.60 per 1M tokens (input/output)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants