---
title: "Discussion on \"Semantic caching\" | Hashnode"
description: "Discussion on \"Semantic caching\". Large language models are getting faster and cheaper. The below charts show progress in OpenAI's GPT family of models over the past year:\nCost per million tokens ($)\n\nTokens per second\n\nRecent releases like Meta's Llama 3 and Gemini Flash have pushed..."
url: "https://hashnode.com/posts/semantic-caching/670d31db97f124d1bfa88a28"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Semantic caching](https://unkey.hashnode.dev/semantic-caching?utm_source=hashnode&utm_medium=feed)

Large language models are getting faster and cheaper. The below charts show progress in OpenAI's GPT family of models over the past year: Cost per million tokens ($) Tokens per second Recent releases like Meta's Llama 3 and Gemini Flash have pushed...

Jun 26, 2024 · 2 min read · unkey.hashnode.dev  
Read the article

-   [#semantic-cache](https://hashnode.com/tag/semantic-cache)
-   [#llm](https://hashnode.com/tag/llm)
-   [#unkey](https://hashnode.com/tag/unkey)

## Written by

[James Perkins](https://hashnode.com/@jamesperkins)

@jamesperkins

  
[View profile](https://hashnode.com/@jamesperkins)

Unkey CEO

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
