Inception Labs
Inception Labs builds Mercury, the first family of commercial-scale diffusion large language models (dLLMs) that generate tokens in parallel for 5-10x faster inference than comparable speed-optimized models. The Inception API is an OpenAI-compatible REST interface exposing Mercury 2 (a 128K-context reasoning dLLM) and Mercury Edit 2 (a coding-focused model) through chat, fill-in-the-middle, and code-edit completion endpoints, with server-sent-event streaming, tool calling, structured JSON-schema outputs, and an "instant" low-latency reasoning mode for realtime voice. Founded in 2024 by Stanford professor Stefano Ermon, the company is backed by Mayfield and ships official Python and TypeScript client libraries plus AWS Bedrock and Azure Foundry enterprise deployment.
Inception Labs publishes 4 APIs on the APIs.io network, including Chat API, Edit API, FIM API, and 1 more. Tagged areas include Artificial Intelligence, Machine Learning, Large Language Models, Diffusion Models, and Generative AI.
Inception Labs’ developer surface includes documentation, API reference, getting-started guide, engineering blog, pricing, signup flow, support, and 20 more developer resources.
Kin Score
APIs 4
Individual APIs this provider publishes, each with its own machine-readable definition.
Inception Labs Chat API
Chat completion endpoints (OpenAI-compatible).
Inception Labs Edit API
Code edit completion endpoints.
Inception Labs FIM API
Fill-in-the-middle code completion endpoints.
Inception Labs Models API
List available models.
Arazzo Workflows 3
Multi-step API workflows described with the Arazzo specification.
_Index
ARAZZOInception — discover a chat model and generate a completion
List the available Mercury chat models, then send a chat completion.
ARAZZOInception — fill-in-the-middle code autocomplete
Confirm a FIM model then generate an inline code completion with Mercury Edit 2.
ARAZZOMCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
inception-labs-mcp.yml
MCP SERVERSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Get Started 3
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 7
Pagination, idempotency, versioning, errors, and events
Scroll for all 7
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 1
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API