Moondream

Moondream is a fast, efficient open vision language model (VLM) from M87 Labs. The Moondream Cloud API turns images into structured output through five Skills — Query (visual question answering), Caption, Detect (bounding boxes), Point (center coordinates), and Segment (SVG path masks) — plus an OpenAI-compatible chat endpoint, an asynchronous Batch API, and cloud finetuning (Lens). Model weights are open and downloadable from Hugging Face; hosted inference is pay-per-token with HIPAA and SOC 2 available. Official Python and Node.js SDKs are published.

Moondream publishes 2 API contracts indexed on the APIs.io network: OpenAI Compatibility API and Skills API. Tagged areas include Company, Artificial Intelligence, Machine Learning, Computer Vision, and Vision Language Model.

The Moondream catalog on APIs.io includes 1 Spectral governance ruleset.

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

🌐 Visit website 📡 Profile data on GitHub

49.9/100 developing ▬ flat Agent 23/100 agent aware Front door AI 5/6 prominent Heartbeat 100/100 alive saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessFreemiumSelf serve⚡ Free to try

1 published contract 3 Agent Skills

Company Artificial Intelligence Machine Learning Computer VisionVision Language ModelObject DetectionImage CaptioningOCR Developer Tools

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 49.9/100 · developing

Contract Quality 2.7 / 19

Developer Ergonomics 10.4 / 15

Access Clarity 13.8 / 15

Operational Transparency 1.8 / 10

Contract Governance 2.9 / 9

Discoverability 5.0 / 8

Regulatory Posture 4.1 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 23/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 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

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/moondream/"><img src="https://apis.io/badge/moondream/card.svg" alt="Moondream on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document
Delegated User Identity +6 pts — a served discovery document listing authorization_code in grant_types_supported (served), else an oauth2 authorizationCode flow or openIdConnect declared in an OpenAPI (documented)

7 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 14.5 — up to +21.4 composite points
Operational Transparency scores 18.4 — up to +10.6 composite points
Contract Governance scores 31.8 — up to +8.2 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/moondream/apis.yml: open an issue on github.com/api-evangelist/moondream to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
RPA and Document AI (RPA marketplaces, intelligent document processing)	distribution	9.6 (thin)	-	1
ONVIF Video Analytics (video surveillance, edge cameras, computer vision)	distribution	9.6 (thin)	-	1

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

Standards implemented 2

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

The OpenAI Interface

declared — publishes a spec that declares them

2 core of 338 operations graded · api-commons/models

OpenAPI

measured — observed by APIs.io (published)

APIs 2

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

Moondream OpenAI Compatibility API

OpenAI-compatible chat completions endpoint.

Moondream Skills API

Moondream vision Skills — query, caption, detect, point, segment.

Open Collections 2

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

Moondream Cloud OpenAI Compatibility API

OPEN COLLECTION

Moondream Cloud OpenAI Compatibility Skills API

OPEN COLLECTION

Agent Skills 3

Packaged agent skills for driving this provider's APIs from an AI assistant.

Caption an image

AGENT SKILL

Detect and locate objects in an image

AGENT SKILL

Ask questions about an image

AGENT SKILL

Moondream API pricing

Prices published by Moondream, read 2026-10-07 from moondream.ai/pricing. A free plan or tier is listed.

Plan	Price
Photon	Free Includes: The world's fastest VLM inference engine — runs everywhere, from edge to server-class hardware.
Models	Free Includes: Open and free to use — hosting them as a cloud service requires our license.
Cloud — Moondream 3.1 9B A2B Real-time input	$0.30/ 1M input tokens
Cloud — Moondream 3.1 9B A2B Real-time output	$1.00/ 1M output tokens
Cloud — Moondream 3.1 9B A2B Batch input	$0.15/ 1M input tokens
Cloud — Moondream 3.1 9B A2B Batch output	$0.50/ 1M output tokens
Cloud — Moondream 3 Preview Real-time output	$2.50/ 1M output tokens
Cloud — Moondream 3 Preview Batch output	$1.25/ 1M output tokens

All 13 plans, limits and sources →

Billed by: 1m output tokens · FinOps profile →

Pricing Plans 2

Published pricing tiers and plan structures.

Moondream Plans Pricing

13 plans

PLANS

Moondream Price Estimates

0 plans

PLANS

Service Levels 1

Uptime the provider promises or reports, as SLA4OAI. Read from its own pages; APIs.io runs no monitors.

Moondream

SLA

FinOps 1

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

Moondream Finops

FINOPS

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Moondream API Rules

60 rules · 58 errors 1 warnings 1 info

SPECTRAL

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Moondream Openapi Overlay

2 actions · update · moondream-openapi.yml

DERIVED

Security Posture 2

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

Moondream Authentication

apiKey/http · 2 schemes

SECURITY

Moondream Domain Security

TLSv1.3 · DMARC

SECURITY

Agentic Access 1

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

Moondream Agentic Access

6 operations · 5 acting · 4 human-in-the-loop

6 operations · 5 acting

AGENTIC

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

SignUp

Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

X-MCPServerCandidate

AgentSkill

LLMsTxt

WellKnown

AgenticAccess

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Lifecycle

Conformance

DataModel

Build 3

SDKs, sample code, and the tooling you integrate with

Packages

Packages

SDKs

SDKs

GitHubOrganization

GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

Compliance

Compliance

DomainSecurity

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

ChangeLog

ChangeLog

Support

Support

Commercial 4

Pricing, plans, and the legal terms of use

Plans

Pricing

TermsOfService

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: moondream
name: Moondream
description: Moondream is a fast, efficient open vision language model (VLM) from M87 Labs. The Moondream Cloud API turns
  images into structured output through five Skills — Query (visual question answering), Caption, Detect (bounding boxes),
  Point (center coordinates), and Segment (SVG path masks) — plus an OpenAI-compatible chat endpoint, an asynchronous Batch
  API, and cloud finetuning (Lens). Model weights are open and downloadable from Hugging Face; hosted inference is pay-per-token
  with HIPAA and SOC 2 available. Official Python and Node.js SDKs are published.
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  gated: none
  gated_source:
  - onboarding
  label: Freemium · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-11-06'
  method: derived
image: https://moondream.ai/apple-touch-icon.png
url: https://raw.githubusercontent.com/api-evangelist/moondream/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- felicis
x-tier: active
x-tier-reason: enriched
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-20'
x-docs-platform: docusaurus
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-04
x-docs-hosting: github-pages
tags:
- Company
- Artificial Intelligence
- Machine Learning
- Computer Vision
- Vision Language Model
- Object Detection
- Image Captioning
- OCR
- Developer Tools
tags_raw:
- Company
- Artificial Intelligence
- Machine Learning
- Computer Vision
- Vision Language Model
- Object Detection
- Image Captioning
- OCR
- Developer Tools
- Machine-Learning
- Computer-Vision
apis:
- aid: moondream:moondream-openai-compatibility-api
  name: Moondream OpenAI Compatibility API
  description: OpenAI-compatible chat completions endpoint.
  humanURL: https://docs.moondream.ai/api
  baseURL: https://api.moondream.ai/v1
  tags:
  - OpenAI Compatibility
  properties:
  - type: OpenAPI
    url: openapi/moondream-openai-compatibility-api-openapi.yml
  - type: Documentation
    url: https://docs.moondream.ai/
  - type: APIReference
    url: https://docs.moondream.ai/api
  - type: GettingStarted
    url: https://docs.moondream.ai/quickstart
  - type: RateLimits
    url: https://docs.moondream.ai/rate-limits
- aid: moondream:moondream-skills-api
  name: Moondream Skills API
  description: Moondream vision Skills — query, caption, detect, point, segment.
  humanURL: https://docs.moondream.ai/api
  baseURL: https://api.moondream.ai/v1
  tags:
  - Skills
  properties:
  - type: OpenAPI
    url: openapi/moondream-skills-api-openapi.yml
  - type: Documentation
    url: https://docs.moondream.ai/
  - type: APIReference
    url: https://docs.moondream.ai/api
  - type: GettingStarted
    url: https://docs.moondream.ai/quickstart
  - type: RateLimits
    url: https://docs.moondream.ai/rate-limits
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Plans
  url: plans/moondream-plans-pricing.yml
- type: Authentication
  url: authentication/moondream-authentication.yml
- type: Conventions
  url: conventions/moondream-conventions.yml
- type: ErrorCatalog
  url: errors/moondream-problem-types.yml
- type: Lifecycle
  url: lifecycle/moondream-lifecycle.yml
- type: Conformance
  url: conformance/moondream-conformance.yml
- type: Compliance
  url: https://moondream.ai/pricing
- type: DataModel
  url: data-model/moondream-data-model.yml
- type: Overlay
  url: overlays/moondream-openapi-overlay.yaml
- type: Packages
  url: packages/moondream-packages.yml
- type: SDKs
  url: packages/moondream-packages.yml
- type: X-MCPServerCandidate
  url: mcp/moondream-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/moondream-llms.txt
- type: WellKnown
  url: well-known/moondream-well-known.yml
- type: ChangeLog
  url: changelog/moondream-changelog.yml
- type: DomainSecurity
  url: security/moondream-domain-security.yml
- type: AgenticAccess
  url: agentic-access/moondream-agentic-access.yml
- type: Website
  url: https://moondream.ai
- type: DeveloperPortal
  url: https://docs.moondream.ai/
- type: Documentation
  url: https://docs.moondream.ai/
- type: APIReference
  url: https://docs.moondream.ai/api
- type: GettingStarted
  url: https://docs.moondream.ai/quickstart
- type: Blog
  url: https://moondream.ai/blog
- type: Pricing
  url: https://moondream.ai/pricing
- type: SignUp
  url: https://moondream.ai/login
- type: TermsOfService
  url: https://moondream.ai/terms
- type: PrivacyPolicy
  url: https://moondream.ai/privacy
- type: GitHubOrganization
  url: https://github.com/m87-labs
- type: Sandbox
  url: https://moondream.ai/c/playground
- type: Support
  url: mailto:sales@moondream.ai
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 19
  pass: local-v1

Moondream API — frequently asked questions

Does Moondream have an API?

Yes. APIs.io lists 2 APIs from Moondream, including Moondream OpenAI Compatibility API and Moondream Skills API.

Is there an OpenAPI specification for the Moondream API?

Yes. APIs.io indexes 2 OpenAPI specifications for Moondream, each linked for download from this page.

How do I authenticate with the Moondream API?

Moondream uses bearer-token authentication (apiKey/http · 2 schemes). The details are profiled on APIs.io as Moondream Authentication.

How much does the Moondream API cost?

Moondream publishes its prices; its Cloud — Moondream 3.1 9B A2B Real-time input plan is $0.30/ 1M input tokens as of 2026-10-07. APIs.io lists 13 pricing plans for Moondream, with each plan's price, limits and inclusions under Pricing on this page.

Is the Moondream API ready for AI agents?

Moondream has a Kin Score of 49.9 out of 100 (developing) and an Agent Readiness score of 23.1 (agent-aware), scored by API Evangelist on 2026-11-06.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/moondream"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/moondream/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/moondream/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.