Heurist LLM Gateway

Heurist Gateway is an OpenAI-compatible LLM API endpoint, built with LiteLLM that allows calling Heurist API using OpenAI format. Switch your LLM provider to Mistral 8x7b (comparable to ChatGPT 3.5 or Claude2) with 3 lines of code and a fraction of the costs. Example below.

For more examples, check https://github.com/heurist-network/dev-examples

Pricing

In the context of Large Language Models (LLMs), a token is a fundamental unit of text that represents a word, part of a word, punctuation, or even a space. Tokens are used by LLMs to process and generate text by breaking down input text into these smaller units.

We use https://classic.yarnpkg.com/en/package/mistral-tokenizer-js to calculate token usage for Mistral models.

Here are some helpful rules of thumb for understanding tokens in terms of lengths:

  • 1 token ~= 4 chars in English

  • 1 token ~= ¾ words

  • 100 tokens ~= 75 words

Or

  • 1-2 sentence ~= 30 tokens

  • 1 paragraph ~= 100 tokens

  • 1,500 words ~= 2048 tokens

The cost of Mixtral 8x7b tokens are priced at 25 credits per 1,000,000 tokens. This rate may be changed in the future. One credit corresponds to x HUE tokens after mainnet TGE (exact ratio depends on HUE price)

Last updated