Helicone
helicone.ai
Actively hiring
AI Development Tools
AI Evaluation & Observability
As featured in
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Financials
Overview
Helicone is a San Francisco company founded in 2023 that provides open-source observability for large language model applications. A one-line proxy change logs every request with cost, latency and prompt detail, and the platform adds caching, rate limiting and evaluation on top. It is widely used by startups that need visibility into model spending and quality from day one.
News
Allowing your users to query ClickHouse directly using raw SQL
How we let Helicone customers run raw SQL against a shared ClickHouse table without ever seeing each other's rows: row policies, custom settings, and an AST parser that is deliberately not part of the security boundary.
Read more
Report
Helicone is joining Mintlify
After three years and 14.2 trillion tokens, we're excited to share that Helicone has been acquired by Mintlify.
Read more
Report
Mintlify acquires Helicone to redefine AI knowledge infrastructure
Mintlify is acquiring Helicone, the open source LLM observability platform and AI gateway. Helicone's team has been building at the frontier of agentic AI, and they're joining to help us build the next generation of AI knowledge infrastructure.
Read more
Report
Chain-of-Draft Prompting: A More Efficient Alternative to Chain of Thought
Learn about the new COD prompting technique, and how its performance and cost stack up against CoT. We also share how you can implement it to improve your AI app's performance and reduce costs.
Read more
Report
The Helicone: Toy Or Mathematical Oddity?
We always enjoy videos from the Mathologer, but we especially liked the recent video on the Helicone, a toy with a surprising connection to mathematics. The toy is cool all by itself, but the video ...
Read more
Report
LLM API Pricing Calculator Compare 300+ AI Model Costs
LLM cost comparison tool to estimate costs for 300+ models across 10+ providers, including OpenAI, Anthropic, Mistral, Claude, and more.
Read more
Report
The Emerging LLM Stack: From Hobbyist Projects to Enterprise-Scale Applications - Helicone
Explore the emerging LLM Stack, designed for building and scaling LLM applications. Learn about its components, including observability, gateways, and experiments, and how it adapts from hobbyist projects to enterprise-scale solutions.
Read more
Report
Prompt Evaluation Explained: Random Sampling vs. Golden Datasets
Crafting high-quality prompts and evaluating them requires both high-quality input variables and clearly defined tasks. In a recent webinar, Nishant Shukla, the senior director of AI at QA Wolf, and Justin Torre, the CEO of Helicone, shared their insights
Read more
Report
11 Best LLM API Providers: Compare Inferencing Performance & Pricing
Compare the top LLM API providers including Together AI, Fireworks, Hyperbolic and Novita. Find the fastest, most cost-effective platforms for your AI applications with real performance metrics and how to integrate Helicone for LLM observability
Read more
Report
How to Monitor Your LLM API Costs and Cut Spending by 90%
Stop watching your OpenAI and Anthropic bills skyrocket. Learn how to optimize prompt engineering, implement strategic caching, use task-specific models, leverage RAG, and monitor costs effectively
Read more
Report
Show more news
Offices
Where the company hires and what each office is for
Cities
1
Hiring now
0
Countries
1
San Francisco
United States
HQ
10-50 est. staff