Models List

List of the models available and their respective costs.

Model NameTypeInputOutput
gpt-3.5-turboText Generation$0.0015 / 1K tokens$0.002 / 1K tokens
gpt-3.5-turbo-16kText Generation$0.0030 / 1K tokens$0.004 / 1K tokens
gpt-4Text Generation$0.03 / 1K tokens$0.06 / 1K tokens
gpt-4-32kText Generation$0.06 / 1K tokens$0.12 / 1K tokens
cohereText Generation$0.015 / 1K tokens$0.015 / 1K tokens
llama-2-70b-chat[Replicate]Text GenerationN/A$0.0014 / second
wizard-mega-13b-awq[Replicate]Uncensored Text GenerationN/A$0.000725 / second
airoboros-llama-2-70b[Replicate]Uncensored Text GenerationN/A$0.0014 / second
replit-code-v1-3b[Replicate]Code GenerationN/A$0.00115 / second
dalle-2Image GenerationN/A$0.02 / image
text-embedding-ada-002Embeddings$0.0001 / 1K tokensN/A
elevenlabsText-To-Speech$0.3 / 1K charsN/A
whisperSpeech-To-Text$0.0001 / secondN/A
  • You can put your own OpenAI and Replicate keys in the dashboard settings.
  • text-embedding-ada-002 is used when creating a Memory/Embeddings or when using a DataLoader.
  • Some features (Web, Memory, Embeddings, DataLoaders, etc...) will increase the number of input tokens. the infos method lets you monitor closely the LLMs token usage.
  • Your total usage costs appears on your dashboard

What’s Next