Inception website screenshot

Inception

Inception Labs builds diffusion-based large language models (dLLMs) branded Mercury. Unlike autoregressive models that emit tokens one at a time, Mercury generates many tokens in parallel through discrete diffusion, running 5-10x faster at roughly half the cost of comparable frontier models. The Inception API is OpenAI-compatible and exposes chat completions (Mercury 2, a reasoning dLLM with a 128K context, tool calling, and structured outputs), plus fill-in-the-middle and next-edit code completions (Mercury Edit 2) for IDE-style autocomplete. It ships official Python and TypeScript SDKs, a streaming/diffusion mode, and enterprise deployment via the Inception API, AWS Bedrock, and Azure AI Foundry. Backed by Amplify Partners.

Inception publishes 4 APIs on the APIs.io network, including Chat API, Edit API, FIM API, and 1 more. Tagged areas include Company, Ai Ml, LLM, Artificial Intelligence, and Diffusion Models.

Inception’s developer surface includes documentation, API reference, getting-started guide, authentication, engineering blog, support, pricing, and 24 more developer resources.

56.0/100 strong ▬ flat Agent 48/100 agent ready Full breakdown ↓
scored 2026-08-17 · rubric v0.11.0
AccessFreemiumSelf serve⚡ Free to try
4 APIs 1 MCP Servers
CompanyAi MlLLMArtificial IntelligenceDiffusion ModelsCode CompletionMachine LearningDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-17 · rubric v0.11.0
Composite quality — 56.0/100 · strong
Contract Quality 16.4 / 25
Developer Ergonomics 12.5 / 20
Commercial Clarity 16.8 / 20
Operational Transparency 0.7 / 13
Governance 1.4 / 12
Discoverability 8.2 / 10
Agent readiness — 48/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 7 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
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: 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 4

Individual APIs this provider publishes, each with its own machine-readable definition.

Inception Chat API

Chat completion endpoints (OpenAI-compatible).

Inception Edit API

Code edit completion endpoints.

Inception FIM API

Fill-in-the-middle code completion endpoints.

Inception Models API

List available models.

Open Collections 5

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Inception Chat API

OPEN COLLECTION

Inception Chat Edit API

OPEN COLLECTION

Inception Chat FIM API

OPEN COLLECTION

Inception Chat Models API

OPEN COLLECTION

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

inception-mcp.yml

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Inception Plans

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Inception Rate Limits

0 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Inception Authentication

http · 1 scheme

SECURITY

Inception Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Inception Agentic Access

7 operations · 3 acting

7 operations · 3 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 3

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

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 2

Status, limits, changes, and where to get help

Commercial 5

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: inception
name: Inception
description: Inception Labs builds diffusion-based large language models (dLLMs) branded Mercury. Unlike autoregressive models
  that emit tokens one at a time, Mercury generates many tokens in parallel through discrete diffusion, running 5-10x faster
  at roughly half the cost of comparable frontier models. The Inception API is OpenAI-compatible and exposes chat completions
  (Mercury 2, a reasoning dLLM with a 128K context, tool calling, and structured outputs), plus fill-in-the-middle and next-edit
  code completions (Mercury Edit 2) for IDE-style autocomplete. It ships official Python and TypeScript SDKs, a streaming/diffusion
  mode, and enterprise deployment via the Inception API, AWS Bedrock, and Azure AI Foundry. Backed by Amplify Partners.
url: https://raw.githubusercontent.com/api-evangelist/inception/refs/heads/main/apis.yml
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://www.inceptionlabs.ai/logo.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- amplify-partners
x-tier: profiled
x-tier-reason: enrichment-pipeline
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Ai Ml
- LLM
- Artificial Intelligence
- Diffusion Models
- Code Completion
- Machine Learning
- Developer Tools
apis:
- aid: inception:inception-chat-api
  name: Inception Chat API
  description: Chat completion endpoints (OpenAI-compatible).
  humanURL: https://docs.inceptionlabs.ai/get-started/get-started
  baseURL: https://api.inceptionlabs.ai
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/inception-chat-api-openapi.yml
  - type: Documentation
    url: https://docs.inceptionlabs.ai/get-started/get-started
  - type: APIReference
    url: https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion
- aid: inception:inception-edit-api
  name: Inception Edit API
  description: Code edit completion endpoints.
  humanURL: https://docs.inceptionlabs.ai/get-started/get-started
  baseURL: https://api.inceptionlabs.ai
  tags:
  - Edit
  properties:
  - type: OpenAPI
    url: openapi/inception-edit-api-openapi.yml
  - type: Documentation
    url: https://docs.inceptionlabs.ai/get-started/get-started
  - type: APIReference
    url: https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion
- aid: inception:inception-fim-api
  name: Inception FIM API
  description: Fill-in-the-middle code completion endpoints.
  humanURL: https://docs.inceptionlabs.ai/get-started/get-started
  baseURL: https://api.inceptionlabs.ai
  tags:
  - FIM
  properties:
  - type: OpenAPI
    url: openapi/inception-fim-api-openapi.yml
  - type: Documentation
    url: https://docs.inceptionlabs.ai/get-started/get-started
  - type: APIReference
    url: https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion
- aid: inception:inception-models-api
  name: Inception Models API
  description: List available models.
  humanURL: https://docs.inceptionlabs.ai/get-started/get-started
  baseURL: https://api.inceptionlabs.ai
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/inception-models-api-openapi.yml
  - type: Documentation
    url: https://docs.inceptionlabs.ai/get-started/get-started
  - type: APIReference
    url: https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://inceptionlabs.ai
- type: DeveloperPortal
  url: https://platform.inceptionlabs.ai/
- type: Documentation
  url: https://docs.inceptionlabs.ai/get-started/get-started
- type: APIReference
  url: https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion
- type: GettingStarted
  url: https://docs.inceptionlabs.ai/get-started/get-started
- type: Authentication
  url: authentication/inception-authentication.yml
- type: Blog
  url: https://www.inceptionlabs.ai/blog
- type: Support
  url: https://docs.inceptionlabs.ai/support/support
- type: Pricing
  url: https://docs.inceptionlabs.ai/get-started/models
- type: SignUp
  url: https://platform.inceptionlabs.ai/auth/login
- type: TermsOfService
  url: https://docs.inceptionlabs.ai/support/tou
- type: PrivacyPolicy
  url: https://docs.inceptionlabs.ai/support/privacy
- type: GitHubOrganization
  url: https://github.com/inception-ai-inc
- type: OpenAPI
  url: openapi/_original/inception-openapi-original.json
- type: LLMsTxt
  url: llms/inception-llms.txt
- type: Packages
  url: packages/inception-packages.yml
- type: SDKs
  url: packages/inception-packages.yml
- type: MCPServer
  url: mcp/inception-mcp.yml
- type: RateLimits
  url: rate-limits/inception-rate-limits.yml
- type: Plans
  url: plans/inception-plans.yml
- type: FinOps
  url: finops/inception-finops.yml
- type: ErrorCatalog
  url: errors/inception-problem-types.yml
- type: Lifecycle
  url: lifecycle/inception-lifecycle.yml
- type: Conventions
  url: conventions/inception-conventions.yml
- type: Conformance
  url: conformance/inception-conformance.yml
- type: DataModel
  url: data-model/inception-data-model.yml
- type: Overlay
  url: overlays/inception-openapi-overlay.yaml
- type: AgentSkill
  url: skills/_index.yml
- type: AgenticAccess
  url: agentic-access/inception-agentic-access.yml
- type: Authentication
  url: authentication/inception-authentication.yml
- type: DomainSecurity
  url: security/inception-domain-security.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence