Mintplex-Labs/anything-llm · critical · Error

LiteLLM must have a valid model set.

Error message

LiteLLM must have a valid model set.

What it means

Thrown by the LiteLLM constructor when no model can be resolved. The constructor uses `modelPreference ?? process.env.LITE_LLM_MODEL_PREF ?? null`, meaning both the constructor argument and the env var must be nullish (null/undefined) for the error to fire. Note: `??` does NOT treat empty string as falsy, so an empty-string modelPreference would be used (and would not trigger this guard).

Source

Thrown at server/utils/AiProviders/liteLLM/index.js:26

} = require("../../helpers/chat/responses");

class LiteLLM {
  constructor(embedder = null, modelPreference = null) {
    const { OpenAI: OpenAIApi } = require("openai");
    if (!process.env.LITE_LLM_BASE_PATH)
      throw new Error(
        "LiteLLM must have a valid base path to use for the api."
      );

    this.className = "LiteLLM";
    this.basePath = process.env.LITE_LLM_BASE_PATH;
    this.openai = new OpenAIApi({
      baseURL: this.basePath,
      apiKey: process.env.LITE_LLM_API_KEY ?? null,
    });
    this.model = modelPreference ?? process.env.LITE_LLM_MODEL_PREF ?? null;

    if (!this.model) throw new Error("LiteLLM must have a valid model set.");
    this.limits = {
      history: this.promptWindowLimit() * 0.15,
      system: this.promptWindowLimit() * 0.15,
      user: this.promptWindowLimit() * 0.7,
    };

    this.embedder = embedder ?? new NativeEmbedder();
    this.defaultTemp = 0.7;
    this.log(`Inference API: ${this.basePath} Model: ${this.model}`);
  }

  log(text, ...args) {
    console.log(`\x1b[36m[${this.className}]\x1b[0m ${text}`, ...args);
  }

  #appendContext(contextTexts = []) {
    if (!contextTexts || !contextTexts.length) return "";
    return (

View on GitHub (pinned to 526360e320)

Solutions

1. Set LITE_LLM_MODEL_PREF in .env to a model name that LiteLLM proxy knows how to route (e.g. 'gpt-3.5-turbo', 'anthropic/claude-2').
2. Select a model in the workspace LLM settings so the modelPreference argument is passed.
3. Check the LiteLLM proxy's /v1/models endpoint for available model identifiers.

Example fix

// before: .env
LITE_LLM_BASE_PATH='http://127.0.0.1:4000'

// after
LITE_LLM_BASE_PATH='http://127.0.0.1:4000'
LITE_LLM_MODEL_PREF='gpt-3.5-turbo'

function validateLiteLLMModel(modelPreference) {
  const model = modelPreference ?? process.env.LITE_LLM_MODEL_PREF ?? null;
  if (!model) {
    throw new Error(
      'No LiteLLM model set. Set LITE_LLM_MODEL_PREF in .env or select a model in workspace settings.'
    );
  }
  return model;
}

const model = validateLiteLLMModel(workspaceModel);

/** @returns {model is string} */
function isValidModelName(model) {
  return typeof model === 'string' && model.trim().length > 0;
}

try {
  const llm = new LiteLLM(embedder, model);
} catch (e) {
  if (e.message.includes('valid model set')) {
    console.error('Configure LITE_LLM_MODEL_PREF or select a model in workspace settings.');
    return null;
  }
  throw e;
}

When it happens

Trigger: Instantiating `new LiteLLM(embedder, model)` where model is null/undefined AND process.env.LITE_LLM_MODEL_PREF is unset. Common when getLLMProvider('litellm') is called with no workspace model selected.

Common situations: The LiteLLM provider was configured with a base path but the model name was never set. The LiteLLM proxy is configured but the user hasn't selected which model to route to. A workspace was created without specifying an LLM model.

Related errors

• KoboldCPP must have a valid model set.
• No Lemonade Model Pref was set.
• LiteLLM must have a valid base path to use for the api.
• LMStudio must have a valid model set.
• GenericOpenAI must have a valid model set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/7517ff8bb6234abf. Report an issue: GitHub.