Provider suggestion: AnyLLM — one connection for 24+ Chinese & international models

Manifest's promise is "connect your agents with any provider" — but for users outside China, several of the providers you support (Moonshot/Kimi, Qwen, and others like DeepSeek, ZhipuAI, MiniMax) require a Chinese phone number and Alipay to sign up directly. That's a hard blocker for most Western users.

I built AnyLLM, an OpenAI-compatible API gateway with 24+ Chinese and international models behind a single key: DeepSeek V4, Qwen3.7-Plus, GLM-5.2, Kimi K2.5/K3, MiniMax M3 — alongside GPT-5 and Gemini. International cards and crypto accepted, pass-through pricing with zero markup, built-in routing and failover.

Why this fits Manifest Same layer-2 pattern. Manifest users already bring their own provider keys. AnyLLM is just one more connection — but one key replaces five separate Chinese provider accounts. Works today. Since Manifest speaks OpenAI-compatible APIs and loads models from /v1/models, AnyLLM can be added as a generic custom provider right now, zero code needed. Complementary, not competing. Manifest handles routing, failover, and analytics; AnyLLM handles model access. Users can even run both — Manifest in front, AnyLLM as a backend. Your Kimi and Qwen users get more. They already want Chinese models (you've added Kimi k3 and qwen3.8-max recently). AnyLLM extends that to the full set — DeepSeek, GLM, MiniMax — under one signup. Proposal 1.Add AnyLLM as a documented provider connection (docs entry or dashboard preset). 2.Or a short "Using an OpenAI-compatible gateway with Manifest" docs section with AnyLLM as the example. Happy to open a PR for either.

(Context: I'm the developer of AnyLLM — happy to provide a sandbox key for testing.) Best, Leo Bennett [[email protected]]