Skip to content

feat: add Brainiall LLM Gateway model provider plugin#2095

Merged
crazywoola merged 3 commits intolanggenius:mainfrom
fasuizu-br:add-brainiall-provider
Feb 26, 2026
Merged

feat: add Brainiall LLM Gateway model provider plugin#2095
crazywoola merged 3 commits intolanggenius:mainfrom
fasuizu-br:add-brainiall-provider

Conversation

@fasuizu-br
Copy link
Contributor

Plugin Submission Form

1. Metadata

2. Submission Type

  • New plugin submission
  • Version update for existing plugin

3. Description

Brainiall LLM Gateway provides access to 113+ AI models from 17 providers (Claude, DeepSeek, Llama, Qwen, Nova, Mistral, and more) through a single OpenAI-compatible API endpoint powered by AWS Bedrock.

Key features:

  • 12 predefined models with accurate pricing (Claude Opus/Sonnet/Haiku, DeepSeek R1/V3, Llama 3.3/4, Qwen 3, Mistral Large 3, Amazon Nova Pro/Micro)
  • Customizable model support for all 113+ models in the catalog
  • Streaming responses
  • Function calling / tool use support
  • Vision support (Claude, Nova Pro, Mistral Large 3, Llama 4 Scout)
  • Competitive pricing via AWS Bedrock

Plugin structure:

  • Uses OAICompatLargeLanguageModel base class for OpenAI-compatible integration
  • Provider credential validation via lightweight model call
  • Both predefined and customizable model configurations
  • Privacy policy included

4. Checklist

  • I have read and followed the Publish to Dify Marketplace guidelines
  • I have read and comply with the Plugin Developer Agreement
  • I confirm my plugin works properly on both Dify Community Edition and Cloud Version
  • I confirm my plugin has been thoroughly tested for completeness and functionality
  • My plugin brings new value to Dify

5. Documentation Checklist

  • Step-by-step setup instructions
  • Detailed usage instructions
  • All required APIs and credentials are clearly listed
  • Connection requirements and configuration details
  • Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

This plugin does not collect any user personal data. All data is sent directly to the Brainiall LLM Gateway API, which proxies requests to AWS Bedrock. No data is stored or processed by the plugin itself.

Privacy Policy

  • I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

Claude DevOps Engineer and others added 3 commits February 23, 2026 18:53
Brainiall provides access to 113+ AI models from 17 providers
(Claude, DeepSeek, Llama, Qwen, Nova, Mistral) through a single
OpenAI-compatible API endpoint powered by AWS Bedrock.

Includes 12 predefined models with full pricing, streaming,
function calling, and vision support. Additional models can be
added via the customizable-model configuration.
Dify plugins CI expects PRs to contain only a single .difypkg file.
Source files are already packaged inside the .difypkg archive.
The dify-plugin-daemon validator requires a minimum 'size' value for
storage.permission even when storage.enabled is false. Remove all
disabled permission subsections (tool, node, endpoint, app, storage)
and keep only the model permission that is actually used, matching
the pattern of other successful model provider plugins.
Copy link
Member

@crazywoola crazywoola left a comment

Choose a reason for hiding this comment

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

PR Review Results

Check Status Required Action
single_difypkg ✅ pass None
pr_language ✅ pass None
unpack ❌ no pass Fix: [Errno 2] No such file or directory: '/Users/crazy...

Next steps

Please address the failing checks and push fixes.

For README language guidelines: https://docs.dify.ai/en/develop-plugin/features-and-specs/plugin-types/multilingual-readme#multilingual-readme

@crazywoola crazywoola merged commit bccc745 into langgenius:main Feb 26, 2026
1 check passed
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