Connection

OpenAI API key

OpenAI Organization ID

(Optional) OpenAI Organization to use when calling the API

Custom URL

(Optional) Custom URL to use when calling the API

Custom headers

(Optional) Static headers sent with every request. Variable expansion is supported.

Text completion/chat models

More information about the pricing: OpenAI Pricing

GPT-5

Prompt cost: $0.00125/1k tokens - Completion cost: $0.01/1k tokens

GPT-5 mini

Prompt cost: $0.00025/1k tokens - Completion cost: $0.002/1k tokens

GPT-5 nano

Prompt cost: $0.00005/1k tokens - Completion cost: $0.0004/1k tokens

GPT-5 Chat

Prompt cost: $0.00125/1k tokens - Completion cost: $0.01/1k tokens
GPT-5 Chat is faster than other GPT-5 models but doesn't support tools or complex reasoning.

GPT-4.1

Prompt cost: $0.002/1k tokens - Completion cost: $0.008/1k tokens

GPT-4.1 mini

Prompt cost: $0.0004/1k tokens - Completion cost: $0.0016/1k tokens

GPT-4.1 nano

Prompt cost: $0.0001/1k tokens - Completion cost: $0.0004/1k tokens

Reasoning models

More information about the pricing: OpenAI Pricing
Output tokens include internal reasoning tokens generated by the model that are not visible in API responses

o4 mini

Prompt cost: $0.00110/1k tokens - Completion cost: $0.00440/1k tokens

o3 mini

Prompt cost: $0.00110/1k tokens - Completion cost: $0.00440/1k tokens

Prompt cost: $0.0020/1k tokens - Completion cost: $0.0080/1k tokens

o3 pro

Prompt cost: $0.0200/1k tokens - Completion cost: $0.0800/1k tokens

Prompt cost: $0.015/1k tokens - Completion cost: $0.060/1k tokens

Image generation models

GPT Image 1

Image generation cost: $0.011 to $0.25 per image

DALL-E 3

Image generation cost: $0.04 to $0.12 per image

Text embedding models

Text embedding v3 Small

Embedding cost: $0.00002/1k tokens

Text embedding v3 Large

Embedding cost: $0.00013/1k tokens

Text embedding Ada v2

Legacy. Embedding cost: $0.0001/1k tokens

Older models

These models are still supported but are usually less performant, slower, more expensive

GPT-4o mini

Prompt cost: $0.00015/1k tokens - Completion cost: $0.0006/1k tokens

GPT-4o

Prompt cost: $0.0025/1k tokens - Completion cost: $0.01/1k tokens

o1 mini

Prompt cost: $0.00110/1k tokens - Completion cost: $0.00440/1k tokens
Deprecated / scheduled for retirement on Oct. 27th, 2025

GPT 3.5 Turbo

Prompt cost: $0.0005/1k tokens - Completion cost: $0.0015/1k tokens

GPT 4 Turbo

Prompt cost: $0.01/1k tokens - Completion cost: $0.03/1k tokens

GPT 4

Prompt cost: $0.03/1k tokens - Completion cost: $0.06/1k tokens

GPT 3.5 Turbo Instruct

Legacy GPTInstruct tuning (not chat optimized) - Prompt cost: $0.0015/1k tokens - Completion cost: $0.002/1k tokens

GPT 3 - Davinci

Legacy GPT3 model - Prompt/Completion costs: $0.002/1k tokens

GPT 3 - Babbage

Legacy GPT3 model - faster and lower cost - Prompt/Completion costs: $0.0004/1k tokens

Custom models

Model id

Required. A model ID supported by OpenAI

Model display name

Used to identify this model in DSS. If empty defaults to the model id

Model type

API Mode

Choose whether the model will use Chat Completions API or Responses API.

Model handling mode

Prompt cost

In $/1k tokens

Completion cost

In $/1k tokens

Embedding cost

In $/1k tokens

Max tokens

Embedding size

Can be fine-tuned

Fine-tuning

Allow fine-tuning
Enable to allow models from this connection in the fine-tuning recipe.

Max tokens API mode