librechat.yaml

# Configuration version (required)
version: 1.1.5

# Cache settings: Set to true to enable caching
cache: true

# Definition of custom endpoints
endpoints:
  # assistants:
  #   disableBuilder: false # Disable Assistants Builder Interface by setting to `true`
  #   pollIntervalMs: 750  # Polling interval for checking assistant updates
  #   timeoutMs: 180000  # Timeout for assistant operations
  #   # Should only be one or the other, either `supportedIds` or `excludedIds`
  #   supportedIds: ["asst_supportedAssistantId1", "asst_supportedAssistantId2"]
  #   # excludedIds: ["asst_excludedAssistantId"]
  custom:
    #groq
    - name: "groq"
      apiKey: "${GROQ_API_KEY}"
      baseURL: "https://api.groq.com/openai/v1/"
      models:
        default:
          [
            'llama3-70b-8192',
            'llama3-8b-8192',
            'llama2-70b-4096',
            'mixtral-8x7b-32768',
            'gemma-7b-it',
          ]
        fetch: true
      titleConvo: true
      titleModel: "mixtral-8x7b-32768"
      summarize: false
      summaryModel: "mixtral-8x7b-32768"
      forcePrompt: false
      modelDisplayLabel: "groq"
      
    # Mistral AI API
    - name: "Mistral"
      apiKey: "user_provided"
      baseURL: "https://api.mistral.ai/v1"
      models:
        default: ["mistral-tiny", "mistral-small", "mistral-medium", "mistral-large-latest"]
        fetch: true
      titleConvo: true
      titleMethod: "completion"
      titleModel: "open-mistral-7b"
      summarize: false
      summaryModel: "open-mistral-7b"
      forcePrompt: false
      modelDisplayLabel: "Mistral"
      dropParams: ["stop", "user", "frequency_penalty", "presence_penalty"]
  
    # Preplexity
    - name: "Perplexity"
      apiKey: "user_provided"
      baseURL: "https://api.perplexity.ai/"
      models:
        default: [
          "llama-3-sonar-small-32k-chat",
          "llama-3-sonar-small-32k-online",
          "llama-3-sonar-large-32k-chat",
          "llama-3-sonar-large-32k-online",
          "mixtral-8x7b-instruct",
          "llama-3-8b-instruct",
          "llama-3-70b-instruct"
          ]
        fetch: false # fetching list of models is not supported
      titleConvo: true
      titleModel: "sonar-medium-chat"
      summarize: false
      summaryModel: "sonar-medium-chat"
      forcePrompt: false
      dropParams: ["stop", "frequency_penalty"]
      modelDisplayLabel: "Perplexity"
  
    # OpenRouter
    - name: 'OpenRouter'
      # Known issue: you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
      apiKey: '${OPENROUTER_KEY}'
      baseURL: 'https://openrouter.ai/api/v1'
      models:
        default: ['meta-llama/llama-3-70b-instruct']
        fetch: true
      titleConvo: true
      titleModel: 'meta-llama/llama-3-8b-instruct'
      # Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
      dropParams: ['stop']
      modelDisplayLabel: 'OpenRouter'