LLM service: consider mentioning `Anannas`

[Haleshot]

Noticed the OpenRouter integration in your docs here.

Wanted to flag Anannas as another option in that space; a unified inference layer with 500+ models (OpenAI, Anthropic, Mistral, Gemini, DeepSeek, etc.) with automatic failover, reserved capacity overflow deeper observability — cache analytics, tool-call metrics, model efficiency scoring. Running production workloads; 100k+ requests with stable latency; 4% markup vs OpenRouter's 5.5%, upto 50% faster in some cases.

If you're open to listing alternatives or additional LLM router integrations alongside OpenRouter, happy to help with the integration docs or example code.

Disclaimer: I'm from Anannas

[markbackman]

Hey, thanks for reaching out. To be listed in Pipecat's docs, you need either an integration in Pipecat's source code or to build a community integration.

You're free to build and maintain a community integration. You can read more about what that entails here:
https://github.com/pipecat-ai/pipecat/blob/main/COMMUNITY_INTEGRATIONS.md

I'm going to close out this issue for tracking purposes, but we can coordinate using this thread, if you have questions about building an integration.

[Haleshot]

Thanks for listing out the steps; will checkout the community integrations contribution guide (and the pipecat/services).