Skip to main content

​
Overview

OpenAI is the most feature-rich provider in Nadoo AI, supporting chat completion, embeddings, text-to-speech, speech-to-text, image generation, and vision — all through a single API key.

​
Setup

1

Get an API Key

Sign up or log in at platform.openai.com. Navigate to API Keys and create a new secret key.
2

Configure in Nadoo

Go to Admin > Model Providers > OpenAI and enter the following:
FieldRequiredDescription
API KeyYesYour OpenAI API key (starts with sk-)
Organization IDNoYour OpenAI organization ID (starts with org-). Only needed if your key belongs to multiple orgs.
3

Test Connection

Click Test to verify the key is valid. Once connected, enable the models you want to use.

​
Available Models

​
Chat / LLM

ModelContext WindowBest For
gpt-4o128K tokensGeneral-purpose, multimodal, fastest GPT-4 class
gpt-4o-mini128K tokensCost-efficient tasks, high-volume workloads
gpt-4-turbo128K tokensComplex reasoning with large context
gpt-3.5-turbo16K tokensSimple tasks, lowest cost

​
Embedding

ModelDimensionsBest For
text-embedding-3-small1536Cost-efficient embeddings for RAG
text-embedding-3-large3072Highest quality embeddings

​
Image Generation

ModelDescription
dall-e-3High-quality image generation from text prompts

​
Speech

ModelCapability
whisper-1Speech-to-text transcription
tts-1Text-to-speech audio generation
tts-1-hdHigh-definition text-to-speech

​
Capabilities

Chat Completion

Conversational AI with streaming, function calling, and JSON mode support.

Vision

Analyze images by sending them alongside text prompts using GPT-4o.

Function Calling

Let the model invoke your application’s tools with structured arguments.

Embeddings

Generate vector representations of text for semantic search and RAG.

Text-to-Speech

Convert text to natural-sounding speech in multiple voices.

Image Generation

Create images from text descriptions using DALL-E 3.
Use CaseRecommended ModelReason
General chatbotgpt-4oBest balance of speed, quality, and cost
High-volume supportgpt-4o-miniLow cost with strong performance
Document analysisgpt-4oVision + long context window
Knowledge base searchtext-embedding-3-smallHigh quality at low cost
Premium RAG pipelinetext-embedding-3-largeMaximum embedding quality
Voice assistantwhisper-1 + tts-1Full speech loop
Image creationdall-e-3Best available image generation

​
Environment Variable

When self-hosting, you can also set the API key via environment variable: 
OPENAI_API_KEY=sk-your-api-key-here
This is picked up automatically by the backend. If both the environment variable and the admin UI configuration are set, the admin UI value takes precedence.

​
Rate Limits and Pricing

OpenAI applies rate limits based on your account tier. Nadoo AI respects these limits and surfaces rate-limit errors clearly in the chat and logs.
Monitor your OpenAI usage at platform.openai.com/usage to avoid unexpected charges. Consider setting a monthly spending limit in your OpenAI account.

​
Troubleshooting

Your API key is invalid or has been revoked. Generate a new key at platform.openai.com/api-keys.
You have hit OpenAI’s rate limit. Wait a moment and retry, or upgrade your OpenAI plan for higher limits.
Some models require specific access tiers. Check your OpenAI account to verify you have access to the model you selected.