Toledo1

Customer Login

Toledo1 Documentation

Complete guide to setting up and using Toledo1

Quick Setup Instructions

  1. Initial Setup:
    • Install Toledo1 and launch the application
    • Navigate to Settings > Presets to view available models
    • Preset 9 (Llama-70b) is enabled by default – free to use
  2. Configure API Keys:
    • Click provider links above to get your API keys
    • Copy your API key from provider website
    • Paste key into corresponding preset’s API Key field
    • Save changes to activate the preset
  3. Select & Enable Models:
    • Choose desired preset based on your needs (see descriptions below)
    • Click the Enable button for your selected preset
    • Return to ChatLog tab to begin using the model
  4. Start Using Toledo1:
    • Type your queries in the chat input
    • Right-click and select ‘Clear’ or type :clear to start a new chat
    • Switch between presets anytime in Settings

Note: Each preset is optimized for different tasks. Experiment with different models to find the best fit for your needs.

Preset 1

  • URL: https://api.openai.com/v1
  • Model: gpt-4o
  • Note: Agentic model, high reasoning, great at coding
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 2

  • URL: https://api.openai.com/v1
  • Model: gpt-4o-mini
  • Note: Low cost, great at coding tasks
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 3

  • URL: https://api.anthropic.com/v1
  • Model: claude-3-5-haiku-latest
  • Note: Low cost, great at coding tasks
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 4

  • URL: https://api.anthropic.com/v1
  • Model: claude-3-5-sonnet-latest
  • Note: Agentic model, high reasoning, great at analytics and coding
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 5

  • URL: https://api.anthropic.com/v1
  • Model: claude-3-opus-latest
  • Note: Great for analytics, writing, math and coding
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 6

  • URL: https://openrouter.ai/api/v1
  • Model: x-ai/grok-beta
  • Note: High reasoning model best at math
  • System: You are a helpful search assistant.
  • Max Context Tokens: 32,000
  • Temperature: 0.8

Preset 7

  • URL: https://openrouter.ai/api/v1
  • Model: qwen/qwen-2.5-72b-instruct
  • Note: Good model for scientific queries
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 8

  • URL: https://openrouter.ai/api/v1
  • Model: google/gemini-pro-1.5
  • Note: High reasoning with vision capability at a low cost
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8

Preset 9 (Free Default)

  • URL: https://api.cerebras.ai/v1
  • Model: llama3.1-70b
  • Note: Fast responses, best for general search queries at a cost of zero
  • System: You are a helpful search assistant.
  • Max Context Tokens: 8,192
  • Temperature: 0.8

Preset 10 (Real-Time)

  • URL: https://api.perplexity.ai
  • Model: llama-3.1-sonar-huge-128k-online
  • Note: Real-Time search, ex: events, weather, stock prices
  • System: You are a helpful search assistant.
  • Max Context Tokens: 128,000
  • Temperature: 0.8