Skip to main content

Overview

OpenAI provides powerful language models including GPT-4o, GPT-4, and the o-series reasoning models.

Supported Models

ModelDescriptionBest For
GPT-4oMost capable multimodalGeneral use
GPT-4o miniFast and affordableDaily tasks
o1Advanced reasoningComplex problems
o1-miniFast reasoningQuick analysis
o1-proProfessional reasoningDeep analysis
o3Latest reasoningComplex reasoning
o3-miniFast o3 variantQuick reasoning
o4-miniNewest mini modelEfficient tasks
GPT-5Next generationComing soon
GPT-5-miniMini variantComing soon
GPT-5-codexCode specializedDevelopment

Setup

1

Get API Key

  1. Go to OpenAI Platform
  2. Sign in or create an account
  3. Navigate to API Keys
  4. Create a new API key
2

Configure in EnConvo

  1. Open SettingsAI Provider
  2. Select OpenAI
  3. Go to Credentials module
  4. Enter your API key
3

Select Model

Choose your preferred model from the dropdown

Configuration

SettingDescriptionDefault
CredentialsAPI key configurationRequired
Model NameModel to useGPT-4o
TemperatureCreativity (0-2)Medium (1)

Reasoning Models

For o-series and GPT-5 models, configure reasoning effort:

o1, o3, o4 Series

LevelDescription
LowFast, economical token usage
MediumBalanced speed and accuracy
HighThorough reasoning, more tokens

GPT-5 Series

LevelDescription
MinimalFastest, minimal reasoning
LowQuick reasoning
MediumBalanced
HighDeep reasoning

Pricing

Check OpenAI Pricing for current rates.
ModelInputOutput
GPT-4o$2.50/1M$10/1M
GPT-4o mini$0.15/1M$0.60/1M
o1$15/1M$60/1M
o1-mini$3/1M$12/1M

Best Practices

  • GPT-4o: Complex tasks, analysis, coding
  • GPT-4o mini: Quick tasks, chat
  • o1/o3: Math, logic, complex reasoning
  • Use GPT-4o mini for simple tasks
  • Set usage limits in OpenAI dashboard
  • Monitor usage in EnConvo settings

Troubleshooting

  • Verify key is copied correctly
  • Check if key has expired
  • Ensure billing is configured
  • Wait and retry
  • Upgrade OpenAI plan
  • Use different model temporarily