Goodfire
Goodfire is an AI interpretability research lab building tools to understand, debug, and intentionally design neural networks by surfacing the internal features (via sparse autoencoders) that drive model behavior. Its Ember API/SDK was the first hosted mechanistic-interpretability API, offering an OpenAI-compatible inference endpoint plus feature discovery, inspection, and steering over open models such as Llama 3.3 70B and Llama 3.1 8B. The company is now consolidating this interpretability work into its Silico platform, which spans large language models, life sciences, and robotics/vision. Backed by Lightspeed, Menlo Ventures, and Wing Venture Capital.
Goodfire publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Machine Learning, Interpretability, and LLM.
Goodfire’s developer surface includes documentation, getting-started guide, signup flow, engineering blog, support, authentication, changelog, and 14 more developer resources.
API Rating
APIs
Ember API
Hosted mechanistic-interpretability API. OpenAI-compatible chat-completions sampling plus feature discovery (semantic/contrastive search, AutoSteer), feature inspection/context,...
Resources
Get Started 3
Portal, sign-up, and the first successful call
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 1
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 3
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 3
Authentication, authorization, and security posture
Operate 3
Status, limits, changes, and where to get help
Commercial 2
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API