Skip to main content

​
Overview

EnConvo supports a wide range of AI providers, giving you the flexibility to choose the best model for your needs. You can use cloud-based APIs or run models locally for complete privacy.

​
Setup Steps

1

Open Settings

Go to Settings → AI Model
2

Select AI Model

Choose your preferred AI model from the list
3

Configure Credentials

Go to Credentials module and enter your API key
4

Select Model

Choose your preferred model from the dropdown

​
Supported Providers

​
Cloud Providers

ProviderDescriptionLink
EnConvo CloudBuilt-in LLM service with points systemdocs
OpenAIGPT-4o, GPT-4, o1, o3 modelsdocs
AnthropicClaude 4, Claude 3.5 Sonnetdocs
GoogleGemini 2.5, Gemini 3 Prodocs
DeepSeekDeepSeek Chat, DeepSeek Reasonerdocs
GroqUltra-fast inferencedocs
xAIGrok modelsdocs
MistralMistral Large, Mistral Smalldocs
QwenAlibaba’s Qwen modelsdocs
CohereCommand R modelsdocs
PerplexitySonar search modelsdocs

​
Aggregators & Gateways

ProviderDescriptionLink
OpenRouterAccess 100+ models via one APIdocs
Vercel AI GatewayMulti-provider gatewaydocs
Together AIOpen-source model hostingdocs
FireworksFast inference platformdocs
SiliconFlowChinese AI platformdocs
302.AIMulti-model platformdocs

​
Enterprise

ProviderDescriptionLink
Azure OpenAIMicrosoft’s OpenAI servicedocs
Cloudflare Workers AIEdge AI inferencedocs
DashScopeAlibaba Cloud AIdocs

​
Local Models

ProviderDescriptionLink
OllamaRun local LLMs easilydocs
LM StudioGUI for local modelsdocs

​
Other Providers

ProviderDescription
MoonShot AIKimi models
SambanovaHigh-performance inference
CerebrasFast inference hardware
PoeMulti-model chat platform
StraicoAI aggregator
AIMagicXMulti-model platform
1min AIQuick AI platform
Arli AICreative AI models

​
Common Settings

All providers share these configuration options:
SettingDescription
Model NameThe specific model to use
TemperatureCreativity level (0-2)
CredentialsAPI key configuration

​
Temperature Settings

LevelValueUse Case
None0Deterministic, factual responses
Low0.5Balanced, slightly creative
Medium1Default, good balance
High1.5More creative
Maximum2Most creative, experimental

​
Advanced Features

​
Extended Thinking (Claude)

For Claude models with reasoning capabilities:
  • Disabled: Standard response
  • Minimal: 1,024 thinking tokens
  • Low: 2,048 thinking tokens
  • Medium: 5,120 thinking tokens
  • High: 10,240 thinking tokens

​
Reasoning Effort (OpenAI o-series)

For OpenAI reasoning models (o1, o3, o4):
  • Low: Fast, economical
  • Medium: Balanced
  • High: More thorough reasoning

​
Gemini Thinking

For Google Gemini 2.5+ models:
  • Disabled: No thinking
  • Auto: Model decides
  • Custom budgets: 512 to 30,000 tokens

​
Google Search Tool

Available for Gemini 2.5 models - grounds responses with real-time web content.

​
URL Context Tool

Available for Gemini 2.5 models - allows including URLs for additional context.

​
Choosing a Provider

  • OpenAI GPT-4o: Excellent all-around performance
  • Anthropic Claude 3.5 Sonnet: Great for writing and analysis
  • Google Gemini 2.5 Pro: Long context, multimodal
  • Anthropic Claude 3.5 Sonnet: Excellent code understanding
  • DeepSeek Coder: Specialized for code
  • OpenAI GPT-4o: Strong coding abilities
  • Groq: Ultra-fast inference
  • Cerebras: Hardware-accelerated
  • Sambanova: High throughput
  • Ollama: Completely local
  • LM Studio: Local with GUI
  • EnConvo Cloud: Pay with points
  • DeepSeek: Very affordable
  • Groq Free Tier: Free usage available