Language models

Multiple models, each with different capabilities and price points. You can think of tokens as pieces of words, where 1,000 tokens are about 750 words. This paragraph is 40 tokens.

Use this tool to manually calculate your input tokens.

GPT-4 Turbo

With 128k context, fresher knowledge and the broadest set of capabilities, GPT-4 Turbo is more powerful than GPT-4 and offered at a lower price.

Learn about GPT-4 Turbo

Model Input Output
gpt-4-0125-preview BT 0.11 / 1K tokens BT 0.33 / 1K tokens

Vision pricing calculator

Name Value
Price per 1K tokens (fixed) BT 0.11
512 x 512 tiles 1 x 1
Total tiles 1
Base tokens 85
Tile tokens 170 x 1 = 170
Total tokens 255
Total price BT 0.02805

GPT-3.5 Turbo

GPT-3.5 Turbo models are capable and cost-effective.

gpt-3.5-turbo-0125 is the flagship model of this family, supports a 16K context window and is optimized for dialog. This is the model currenty being used in our system.

Learn about GPT-3 Turbo

Model Input Output
gpt-3.5-turbo-0125 BT 0.0055 / 1K tokens BT 0.0165 / 1K tokens

Other models

Image models

Build DALL·E directly into your apps to generate and edit novel images and art. DALL·E 3 is the highest quality model and DALL·E 2 is optimized for lower cost.

Learn about image generation

Model Quality Resolution Price
DALL·E 3 Standard 1024x1024 BT 0.44 / image
Standard 1024x1792, 1792x1024 BT 0.88 / image
DALL·E 3 HD 1024x1024 BT 0.88 / image
HD 1024x1792, 1792x1024 BT 1.32 / image
DALL·E 2 1024x1024 BT 0.23 / image
512x512 BT 0.198 / image
DALL·E 2 256x256 BT 0.176 / image

Audio models

Whisper can transcribe speech into text and translate many languages into English.

Text-to-speech (TTS) can convert text into spoken audio.

Model Usage
Whisper BT 0.066 / minute (rounded to the nearest second)
TTS BT 0.165 / 1K characters
TTS HD BT 0.33 / 1K characters

Please be informed that the voice you are currently hearing is generated by artificial intelligence technology for Text-to-Speech synthesis. This voice is not that of a human, but rather a computer-generated voice. We want to ensure transparency and clarity in our communication, and we appreciate your understanding. If you have any questions or concerns, please feel free to reach out to us