AnythingLLM

The Generic OpenAI provider.

Uses the OpenAI Chat Completions API. AnythingLLM docs

Public

In Settings › AI Providers › LLM, choose Generic OpenAI, fill these in and save.

Fig. I, LLM Preference

# Settings › AI Providers › LLM › Generic OpenAI
Base URL
  https://api.pollio.ai/v1
API Key
  pl-live-...
Selected Model
  deepseek/deepseek-v4.1-flash
Model context window
  1048576
Max Tokens
  4096

Private

Start pollio proxy on your machine, then point AnythingLLM at it instead.

Fig. II, LLM Preference

# Settings › AI Providers › LLM › Generic OpenAI
Base URL
  http://127.0.0.1:8787/v1
API Key
  pl-live-...
Selected Model
  deepseek/deepseek-v4.1-flash
Model context window
  1048576
Max Tokens
  4096

AnythingLLM sends Max Tokens with every request, and it defaults to 1024, so set it to what you need. If it runs in Docker, 127.0.0.1 is the container itself: for the private setup, use host.docker.internal instead.

Names and logos belong to their owners. No endorsement implied.