Skip to content

provider: add Avian as a new LLM provider#1541

Open
avianion wants to merge 1 commit intoPortkey-AI:mainfrom
avianion:feat/add-avian-provider
Open

provider: add Avian as a new LLM provider#1541
avianion wants to merge 1 commit intoPortkey-AI:mainfrom
avianion:feat/add-avian-provider

Conversation

@avianion
Copy link

Description:

  • Add Avian as a new OpenAI-compatible LLM provider
  • Avian provides access to multiple LLM models through a unified API at https://api.avian.io/v1
  • Supports chat completions, streaming, and function calling
  • Auth via Bearer token (AVIAN_API_KEY)
  • Available models:
    • deepseek/deepseek-v3.2 — 164K context, 65K max output
    • moonshotai/kimi-k2.5 — 131K context, 8K max output
    • z-ai/glm-5 — 131K context, 16K max output
    • minimax/minimax-m2.5 — 1M context, 1M max output

Files changed:

  • src/providers/avian/api.ts — API config (base URL, auth headers, endpoint routing)
  • src/providers/avian/chatComplete.ts — Stream chunk transform for SSE streaming
  • src/providers/avian/index.ts — Provider config using open-ai-base helpers
  • src/globals.ts — Added AVIAN constant and registered in VALID_PROVIDERS
  • src/providers/index.ts — Registered AvianConfig in the providers map

Tests Run/Test cases added:

  • TypeScript compilation passes (npx tsc --noEmit — no avian-related errors)
  • Build succeeds (npm run build)
  • Gateway starts successfully (node start-test.js)
  • Prettier formatting verified on all new files

Type of Change:

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Documentation update
  • Refactoring (no functional changes)

Add Avian (https://avian.io) as a new OpenAI-compatible provider.

Avian provides access to multiple LLM models through a unified
OpenAI-compatible API at https://api.avian.io/v1, supporting chat
completions, streaming, and function calling.

Available models:
- deepseek/deepseek-v3.2 (164K context)
- moonshotai/kimi-k2.5 (131K context)
- z-ai/glm-5 (131K context)
- minimax/minimax-m2.5 (1M context)

Auth: Bearer token via API key.
@avianion
Copy link
Author

Hi @VisargD @roh26it @vrushankportkey — this PR adds Avian (https://avian.io) as a new OpenAI-compatible provider. It follows the existing open-ai-base pattern used by other providers. Would love your review when you get a chance!

@avianion
Copy link
Author

avianion commented Mar 5, 2026

Friendly follow-up — this PR is still active and ready for review. Would appreciate a look when you get a chance! cc @VisargD @roh26it

@avianion
Copy link
Author

avianion commented Mar 5, 2026

Friendly follow-up — this PR is still active and ready for review. All feedback has been addressed. Would appreciate a look when you get a chance! cc @VisargD @roh26it

@avianion
Copy link
Author

avianion commented Mar 5, 2026

Hey @VisargD @narengogi — friendly follow-up on this PR. Avian is an OpenAI-compatible inference provider that's already live and powering apps like ISEKAI ZERO. This is a lightweight integration (standard OpenAI-compatible endpoint) and we're happy to address any feedback or make adjustments. Would love to get this merged if you have a moment to review. Thanks!

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.

1 participant