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 1 API on the APIs.io network: Inception API. 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.

🌐 Visit website 📡 Source on GitHub
43.1/100 thin Agent 65/100 agent native Full breakdown ↓
scored 2026-07-20 · rubric v0.4
1 APIs 1 MCP Servers 0 Features
Artificial IntelligenceMachine LearningLarge Language ModelsDiffusion ModelsGenerative AICode CompletionLLM APIOpenAI CompatibleDeveloper ToolsCompany

API Rating

API Evangelist API Evangelist Rating How this is scored →
scored 2026-07-20 · rubric v0.4
Composite quality — 43.1/100 · thin
Contract Quality 9.4 / 25
Developer Ergonomics 14.8 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 65/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/inception-labs: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs

Inception API

OpenAI-compatible LLM API for the Mercury diffusion language models — chat, fill-in-the-middle, and code-edit completions with streaming, tool calling, and structured outputs. A...

MCP Servers

inception-labs-mcp.yml

MCP SERVER

Arazzo Workflows

_Index

ARAZZO

Inception — discover a chat model and generate a completion

List the available Mercury chat models, then send a chat completion.

ARAZZO

Inception — fill-in-the-middle code autocomplete

Confirm a FIM model then generate an inline code completion with Mercury Edit 2.

ARAZZO

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 AgenticAccess
AgenticAccess
 AgentSkill
AgentSkill

Design & Contract 7

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 DataModel
DataModel
 Conformance
Conformance
 Arazzo
Arazzo
 Arazzo
Arazzo

Scroll for all 7

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 SDKs
SDKs
 Packages
Packages

Access & Security 2

Authentication, authorization, and security posture

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support
Support

Commercial 3

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Source (apis.yml)

apis.yml Raw ↑ 
aid: inception-labs
name: Inception Labs
description: 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.
url: https://raw.githubusercontent.com/api-evangelist/inception-labs/refs/heads/main/apis.yml
image: https://docs.inceptionlabs.ai/logo.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- mayfield
x-tier: enriched
x-tier-reason: portfolio-lead-enriched
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Artificial Intelligence
- Machine Learning
- Large Language Models
- Diffusion Models
- Generative AI
- Code Completion
- LLM API
- OpenAI Compatible
- Developer Tools
- Company
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: inception-labs-api
  name: Inception API
  description: OpenAI-compatible LLM API for the Mercury diffusion language models — chat, fill-in-the-middle, and code-edit
    completions with streaming, tool calling, and structured outputs. Authenticated with a Bearer API key.
  humanURL: https://docs.inceptionlabs.ai/get-started/get-started
  baseURL: https://api.inceptionlabs.ai/v1
  tags:
  - Large Language Models
  - Chat Completions
  - Code Completion
  properties:
  - type: DeveloperPortal
    url: https://platform.inceptionlabs.ai
  - type: Documentation
    url: https://docs.inceptionlabs.ai
  - type: APIReference
    url: https://docs.inceptionlabs.ai/api-reference
  - type: GettingStarted
    url: https://docs.inceptionlabs.ai/get-started/get-started
  - type: OpenAPI
    url: openapi/inception-labs-openapi-original.json
  - type: Overlay
    url: overlays/inception-labs-openapi-overlay.yaml
common:
- type: Website
  url: https://inceptionlabs.ai
- type: DeveloperPortal
  url: https://platform.inceptionlabs.ai
- type: Documentation
  url: https://docs.inceptionlabs.ai
- type: APIReference
  url: https://docs.inceptionlabs.ai/api-reference
- type: GettingStarted
  url: https://docs.inceptionlabs.ai/get-started/get-started
- type: Blog
  url: https://www.inceptionlabs.ai/blog
- type: GitHubOrganization
  url: https://github.com/inception-ai-inc
- type: Pricing
  url: https://www.inceptionlabs.ai/models
- type: SignUp
  url: https://platform.inceptionlabs.ai
- type: Support
  url: https://docs.inceptionlabs.ai/support/support
- type: TermsOfService
  url: https://docs.inceptionlabs.ai/support/tou
- type: PrivacyPolicy
  url: https://docs.inceptionlabs.ai/support/privacy
- type: SDKs
  url: packages/inception-labs-packages.yml
- type: Packages
  url: packages/inception-labs-packages.yml
- type: Authentication
  url: authentication/inception-labs-authentication.yml
- type: Conventions
  url: conventions/inception-labs-conventions.yml
- type: ErrorCatalog
  url: errors/inception-labs-problem-types.yml
- type: Lifecycle
  url: lifecycle/inception-labs-lifecycle.yml
- type: DataModel
  url: data-model/inception-labs-data-model.yml
- type: Conformance
  url: conformance/inception-labs-conformance.yml
- type: MCPServer
  url: mcp/inception-labs-mcp.yml
- type: LLMsTxt
  url: llms/inception-labs-llms.txt
- type: AgenticAccess
  url: agentic-access/inception-labs-agentic-access.yml
- type: DomainSecurity
  url: security/inception-labs-domain-security.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Arazzo
  name: Discover a chat model and generate a completion
  url: arazzo/inception-labs-chat-completion.arazzo.yml
- type: Arazzo
  name: Fill-in-the-middle code autocomplete
  url: arazzo/inception-labs-code-autocomplete.arazzo.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence