Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.enconvo.ai/llms.txt

Use this file to discover all available pages before exploring further.

Overview

EnConvo supports 25+ AI providers and hundreds of models. This guide helps you choose the right model for your specific needs, balancing quality, speed, cost, and privacy.

Quick Recommendation

Not sure where to start? Here are our top picks for common scenarios:
ScenarioRecommended ModelWhy
General daily useClaude Haiku 4.5Fast, affordable, handles most tasks well
Complex reasoningClaude Sonnet 4.5 or GPT-5Deep analysis, multi-step problem solving
Coding tasksClaude Sonnet 4.5Best code understanding and generation
Creative writingGPT-5 or Claude Opus 4Natural language, creative expression
Long documentsGemini 2.5 Flash1M token context window
Math and scienceDeepSeek V3Specialized reasoning capabilities
Privacy-firstOllama (Llama 3)Runs entirely on your Mac
Budget-friendlyGemini 2.5 Flash LiteExcellent quality at lowest cost

Model Capability Comparison

Flagship Models

ModelProviderContextMultimodalTool UseStrengths
GPT-5OpenAI128KYesYesBroad knowledge, creative tasks, vision
Claude Sonnet 4.5Anthropic200KYesYesCoding, analysis, instruction following
Claude Opus 4Anthropic200KYesYesComplex reasoning, agentic tasks
Gemini 2.5 ProGoogle1MYesYesLong context, research, multimodal
Gemini 2.5 FlashGoogle1MYesYesFast, efficient, long context
DeepSeek V3DeepSeek128KYesYesMath, coding, reasoning at low cost
GrokxAI128KYesYesReal-time knowledge, reasoning

Cost-Efficient Models

ModelProviderContextBest ForRelative Cost
GPT-5 MiniOpenAI128KGeneral tasks, fast responsesLow
Claude Haiku 4.5Anthropic200KQuick tasks, high volumeLow
Gemini 2.5 Flash LiteGoogle1MBudget-friendly, long contextLowest
DeepSeek V3DeepSeek128KCoding, math at great valueLow
Groq (Llama 3)Groq128KUltra-fast inferenceLow

Local Models (Free, Private)

ModelPlatformRAM NeededBest For
Llama 3.3 70BOllama40+ GBMost capable local model
Llama 3.1 8BOllama8 GBGeneral tasks, fast
Qwen 2.5 72BOllama40+ GBMultilingual, coding
Mistral SmallOllama8 GBEuropean languages
CodeLlama 34BOllama20+ GBCode-focused tasks
DeepSeek Coder V2Ollama16+ GBCoding at moderate size
Any GGUF modelLM StudioVariesCustom model loading

Choosing by Use Case

Coding and Development

Claude Sonnet 4.5 is the top choice for coding tasks:
  • Excellent code understanding across 20+ languages
  • Generates clean, well-structured code
  • Strong at debugging and refactoring
  • Understands complex codebases and architectures
  • 200K context for large code files

Writing and Content Creation

GPT-5 excels at creative tasks:
  • Natural, engaging prose
  • Strong narrative structure
  • Good at maintaining voice and tone
  • Excellent vocabulary and style variety
Claude Opus 4 is also excellent for nuanced, long-form writing.

Research and Analysis

Gemini 2.5 Pro or Gemini 2.5 Flash with their 1M token context:
  • Process entire books, research papers, or codebases
  • Cross-reference information across hundreds of pages
  • Enable Google Search grounding for real-time information
  • URL Context tool for analyzing web pages directly

Math, Science, and Reasoning

TaskRecommended ModelNotes
Advanced mathDeepSeek V3Strong mathematical reasoning
Physics/ChemistryClaude Sonnet 4.5 or GPT-5Good scientific knowledge
Data analysisGemini 2.5 ProHandles large datasets with long context
Logic puzzlesClaude Opus 4Excels at complex reasoning chains
StatisticsDeepSeek V3Cost-effective for quantitative tasks

Multilingual Tasks

Language GroupBest Cloud ModelBest Local Model
EnglishAny top-tier modelLlama 3.1 8B
ChineseDeepSeek V3, QwenQwen 2.5
Japanese/KoreanGPT-5, ClaudeQwen 2.5
EuropeanClaude, GPT-5Mistral
MultilingualGemini 2.5Qwen 2.5 72B

Cloud vs Local: Decision Guide

Choose Cloud Models When:

  • You need the highest accuracy and capability
  • You work with many different tasks throughout the day
  • You have reliable internet access
  • Speed of response matters more than privacy
  • You need the latest knowledge and capabilities

Choose Local Models When:

  • Privacy is critical (sensitive data, proprietary code)
  • You work offline frequently
  • You want zero ongoing API costs
  • You have an Apple Silicon Mac with sufficient RAM
  • Your tasks are well-suited to smaller models
Most users benefit from combining both:
Task TypeUse
Sensitive code reviewLocal (Ollama)
Creative writingCloud (GPT-5 / Claude)
Quick translationsCloud (fast model)
Confidential documentsLocal (Ollama)
Complex researchCloud (Gemini with long context)
Daily chatCloud (Haiku / GPT-5 Mini)

Multimodal Capabilities

Models that can understand images, audio, and other media:
ModelImagesAudioVideoDocuments
GPT-5YesYesNoYes
Claude Sonnet 4.5YesNoNoYes
Gemini 2.5 ProYesYesYesYes
Gemini 2.5 FlashYesYesYesYes
GrokYesNoNoYes
If you frequently work with images (screenshots, diagrams, photos), choose a model with vision capabilities. Gemini models have the broadest multimodal support including video understanding.

Cost Optimization Strategies

Route simple tasks to cheap models and complex tasks to powerful ones:
  • Quick questions: Claude Haiku 4.5 or GPT-5 Mini
  • Standard work: Claude Sonnet 4.5 or GPT-5
  • Complex analysis: Claude Opus 4 or Gemini 2.5 Pro
The Enconvo Cloud Plan provides access to all major providers through a single subscription with points-based pricing. This avoids managing multiple API keys and lets you switch models freely.
If you run hundreds of queries daily, local models via Ollama eliminate per-query costs entirely. A one-time hardware investment pays for itself quickly.
Sending unnecessary context increases costs. Use EnConvo’s context awareness features to include only relevant information, and leverage knowledge base RAG instead of stuffing entire documents into the prompt.
Bigger is not always better. For simple tasks (formatting, extraction, classification), a small fast model delivers identical results at a fraction of the cost of a flagship model.

Configuring Models in EnConvo

1

Open Settings

Navigate to any command that uses an AI model (e.g., AI Chat, Translator, Agent).
2

Select AI Model Provider

Find the AI Model Provider setting and click to change it. You will see all configured providers.
3

Choose Provider and Model

Select the provider (OpenAI, Anthropic, Google, etc.) and then choose the specific model from the Model Name dropdown.
4

Adjust Temperature

Set the temperature based on your needs:
  • 0 (none): Deterministic, consistent responses — best for coding, math, extraction
  • 0.5 (low): Slightly varied — good for general tasks
  • 1.0 (medium): Balanced creativity — default for most use cases
  • 1.5 (high): More creative — good for brainstorming, writing
  • 2.0 (maximum): Most varied — experimental, creative exploration

Provider Setup Quick Reference

ProviderSetupAPI Key Source
Enconvo CloudBuilt-in, no setupEnconvo subscription
OpenAIAdd API keyplatform.openai.com
AnthropicAdd API keyconsole.anthropic.com
GoogleAdd API keyai.google.dev
DeepSeekAdd API keyplatform.deepseek.com
GroqAdd API keyconsole.groq.com
OllamaInstall Ollama appFree, no key needed
LM StudioInstall LM Studio appFree, no key needed
OpenRouterAdd API keyopenrouter.ai
MistralAdd API keyconsole.mistral.ai
PerplexityAdd API keyperplexity.ai
xAIAdd API keyconsole.x.ai
For detailed setup instructions for each provider, see the Providers section of the documentation.

Switching Models On-the-Fly

In the AI Chat interface, you can switch models at any time:
  1. Click the model name in the chat header
  2. Select a different model from the dropdown
  3. Continue your conversation with the new model
This is useful for:
  • Starting with a fast model for quick back-and-forth, then switching to a powerful model for the final task
  • Trying the same prompt with different models to compare results
  • Using a vision model when you need to share an image

Provider Setup

Configure AI providers and API keys

Local LLM

Set up Ollama and local models

AI Chat

Use models in conversation

Enconvo Cloud Plan

Access all models with one subscription