Skip to content

feat: add Chuizi.AI model provider plugin#2243

Open
binbor111 wants to merge 2 commits intolanggenius:mainfrom
binbor111:feat/add-chuizi-provider
Open

feat: add Chuizi.AI model provider plugin#2243
binbor111 wants to merge 2 commits intolanggenius:mainfrom
binbor111:feat/add-chuizi-provider

Conversation

@binbor111
Copy link
Copy Markdown

Summary

Add Chuizi.AI model provider plugin (packaged as .difypkg).

Chuizi.AI is a unified AI gateway providing access to 100+ models across 16 providers through a single OpenAI-compatible endpoint.

Plugin contents

  • OAI-compatible LLM provider
  • API key authentication
  • 9 predefined models: Claude (Sonnet/Opus/Haiku), GPT-4.1, o4-mini, Gemini 2.5 Pro, DeepSeek V3.2/R1
  • Custom model support via provider/model naming
  • Base URL: https://api.chuizi.ai/v1

Get API key: app.chuizi.ai

binbor111 and others added 2 commits April 3, 2026 07:09
Chuizi.AI is a unified AI gateway providing access to 100+ models
across 16 providers through a single OpenAI-compatible endpoint.

Packaged plugin includes:
- 9 predefined LLM models (Claude, GPT, Gemini, DeepSeek)
- Custom model support via provider/model naming
- API key authentication
- Base URL: https://api.chuizi.ai/v1
- Add 10 new models: Claude Sonnet 4.5, GPT-5/5-mini/5.1, Gemini 2.5
  Flash, Qwen3 Max, Grok 4, Kimi K2.5, GLM-4.6
- Correct pricing on all existing models to reflect Chuizi's 1.05
  gateway margin on upstream list prices
- Update manifest description to mention 17 providers (was 16) and
  native Anthropic/Gemini protocol support
- Bump version 0.1.0 -> 0.2.0
@xtaq
Copy link
Copy Markdown

xtaq commented Apr 8, 2026

Unified model gateways are a really useful test case for what buyers actually use to shortlist providers.

If an enterprise-facing marketplace could only surface 3 first-screen signals for a provider like Chuizi.AI, which 3 would you prioritize?

  1. API compatibility details (how cleanly it matches OpenAI-style expectations)
  2. Upstream model / region availability
  3. Pricing predictability (rate card clarity, passthrough vs markup expectations)
  4. Reliability / rate-limit behavior
  5. Compliance / data-handling boundary

My current bias is that compatibility gets a provider onto the shortlist, but region/data boundary + pricing predictability are what decide whether a team actually connects it.

Curious which three come up first for real users.

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