Upstage

Upstage is a Korean AI company offering the Solar LLM family and document AI (Document Parse, OCR, Information Extract, Classify) through Upstage Console at https://api.upstage.ai/v1. Its Solar Decide model (beta, built on Solar Mini 4) is exposed at POST /v1/systemone, a System One-style endpoint taking a state plus typed questions (choice, score, noul) and returning calibrated decisions; output tokens are not billed. API references are published as markdown under console.upstage.ai/api/ with an llms.txt index; the reference pages cite OpenAPI files (e.g. ./openapi/openapi-systemone.yaml) that are not publicly retrievable, so no provider-published OpenAPI was saved.

Upstage is listed with 12 APIs on the APIs.io network, including System One API, and 11 more. Tagged areas include Artificial Intelligence, LLM, Document AI, OCR, and Decision Support.

The Upstage catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

Upstage’s developer surface includes authentication, support, sandbox, engineering blog, documentation, API reference, changelog, and 30 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

34.7/100 thin ▼ -8.8 Agent 24/100 agent aware Heartbeat 100/100 alive Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

12 APIs 2 MCP Servers

Artificial Intelligence LLM Document AI OCR Decision Support Structured Outputs Embeddings

Kin Score

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

Composite quality — 34.7/100 · thin

Contract Quality 5.2 / 19

Developer Ergonomics 5.2 / 15

Access Clarity 1.6 / 15

Operational Transparency 6.3 / 10

Contract Governance 2.0 / 9

Discoverability 5.9 / 8

Regulatory Posture 2.9 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 24/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

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 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 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/upstage-ai/"><img src="https://apis.io/badge/upstage-ai/card.svg" alt="Upstage 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):

Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author
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)

8 more unmet checks in the Agent Readiness table above.

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

Contract Quality scores 27.7 — up to +18.1 composite points
Access Clarity scores 10.5 — up to +17.9 composite points
Developer Ergonomics scores 34.5 — up to +13.1 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/upstage-ai/apis.yml: open an issue on github.com/api-evangelist/upstage-ai 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
Typed Decision Models	covered	47.9	-	-
Retrieval, Vector and RAG	covered	47.9	-	-
RPA and Document AI (RPA marketplaces, intelligent document processing)	covered	47.9	-	-
Hugging Face Hub Organisations	covered	47.9	-	-

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.

Model Context Protocol (MCP)

measured — observed by APIs.io (documented)

OpenAPI

measured — observed by APIs.io (published)

APIs 12

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

Upstage Chat Completions API

POST /chat/completions for Solar models (OpenAI-compatible).

Upstage Responses API

OpenAI-compatible Responses API with structured outputs, tool calling, reasoning and file_search.

Upstage Embeddings API

Solar Embedding vectors for passages and queries.

Upstage Document Parse API

Parse documents into structured HTML or Markdown, sync and async.

Upstage Document OCR API

OCR for scanned documents and images.

Upstage Universal Information Extraction API

Schema-driven structured extraction from documents, with async and schema generation.

Upstage Document Classification API

Classify documents into user-defined classes.

Upstage Groundedness Check API

Check LLM answers against source context.

Upstage Translation API

Korean, English and Japanese translation models.

Upstage Vector Stores API

Create, manage and search vector stores and file batches for file search.

Upstage Agents API

Run Studio document agents: upload files and create/retrieve jobs.

Upstage System One API

The System One API from Upstage — 1 operation(s) for system one.

Scroll for all 12

MCP Servers 2

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

MCP server manifest

MCP server requiring an API key; 2 tools listed.

MCP SERVER

MCP server guide

MCP SERVER

Upstage API pricing

Rate limits

Solar Pro 4 Tier 0 RPM: 100 RPM (Requests per minute)
Solar Pro 4 Tier 0 TPM: 250,000 TPM (Tokens per minute)
Solar Pro 4 Tier 1 (Explore) RPM: 400 RPM (Requests per minute)

All 150 limits →

Rate Limits 1

Documented rate limits and quota policies.

Upstage Ai Rate Limits

150 limits

RATE LIMITS

Service Levels 1

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

Upstage

SLA

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Upstage Ai Context

5 classes · 15 properties

JSON-LD

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Upstage API Rules

16 rules · 14 errors 1 warnings 1 info

SPECTRAL

JSON Schema 2

Standalone JSON Schema definitions for this provider's data models.

SystemOneRequest

3 properties

JSON SCHEMA

SystemOneResponse

3 properties

JSON SCHEMA

Security Posture 2

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

Upstage Ai Authentication

1 scheme

SECURITY

Upstage Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 1

Portal, sign-up, and the first successful call

Sandbox

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

LLMsTxt

WellKnown

LLMsTxt

MCPServer

MCPServer

Design & Contract 8

Pagination, idempotency, versioning, errors, and events

Spectral

JSONLD

Vocabulary

DataModel

Lifecycle

ErrorCatalog

Conformance

ErrorCodes

Scroll for all 8

Build 3

SDKs, sample code, and the tooling you integrate with

SDKs

SDKs

Packages

Packages

GitHubOrganization

GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

SecurityTxt

SecurityTxt

DomainSecurity

DomainSecurity

Operate 7

Status, limits, changes, and where to get help

RateLimits

Deprecation

Support

StatusPage

RateLimits

ChangeLog

SLA

Scroll for all 7

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 3

The organization behind the API

Newsroom

Newsroom

Blog

Blog

Website

Website

Other 3

Properties that don't map to a standard resource type

Hosts

Hosts

Vendors

Vendors

Leadership

Leadership

Source (apis.yml)

aid: upstage-ai
name: Upstage
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  probe_state: unreadable
  source:
  - authentication
  - rate-limits
  - security
  generated: '2026-11-06'
  method: derived
image: https://cdn.prod.website-files.com/6743d5190bb2b52f38e99e37/680a25ee07a17eed6deeff74_OG.avif
description: Upstage is a Korean AI company offering the Solar LLM family and document AI (Document Parse, OCR, Information
  Extract, Classify) through Upstage Console at https://api.upstage.ai/v1. Its Solar Decide model (beta, built on Solar Mini
  4) is exposed at POST /v1/systemone, a System One-style endpoint taking a state plus typed questions (choice, score, noul)
  and returning calibrated decisions; output tokens are not billed. API references are published as markdown under console.upstage.ai/api/
  with an llms.txt index; the reference pages cite OpenAPI files (e.g. ./openapi/openapi-systemone.yaml) that are not publicly
  retrievable, so no provider-published OpenAPI was saved.
url: https://raw.githubusercontent.com/api-evangelist/upstage-ai/refs/heads/main/apis.yml
x-type: company
x-source: harvest:direct-request
specificationVersion: '0.20'
created: '2026-10-12'
modified: '2026-10-12'
tags:
- Artificial Intelligence
- LLM
- Document AI
- OCR
- Decision Support
- Structured Outputs
- Embeddings
tags_raw:
- Artificial Intelligence
- Large Language Models
- Document AI
- OCR
- Decision Support
- Structured Outputs
- Embeddings
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
common:
- type: RateLimits
  url: rate-limits/upstage-ai-rate-limits.yml
- type: Spectral
  url: rules/upstage-ai-rules.yml
- type: JSONLD
  url: json-ld/upstage-ai-context.jsonld
- type: Vocabulary
  url: vocabulary/upstage-ai-vocabulary.yml
- type: DataModel
  url: data-model/upstage-ai-data-model.yml
- type: Authentication
  url: authentication/upstage-ai-authentication.yml
- type: Deprecation
  url: https://console.upstage.ai/docs/models/history
- type: Lifecycle
  url: lifecycle/upstage-ai-lifecycle.yml
- type: ErrorCatalog
  url: errors/upstage-ai-problem-types.yml
- type: Conformance
  url: conformance/upstage-ai-conformance.yml
- type: LLMsTxt
  url: llms/upstage-ai-llms.txt
- type: SecurityTxt
  url: well-known/upstage-ai-support-security.txt
- type: WellKnown
  url: well-known/upstage-ai-well-known.yml
- type: Hosts
  url: hosts/upstage-ai-hosts.yml
- type: Vendors
  url: vendors/upstage-ai-vendors.yml
- type: SDKs
  url: packages/upstage-ai-packages.yml
- type: Packages
  url: packages/upstage-ai-packages.yml
- type: Support
  url: https://support.upstage.ai
- type: StatusPage
  url: https://status.upstage.ai/
- type: Sandbox
  url: https://console.upstage.ai/playground/chat
- type: Newsroom
  url: https://www.upstage.ai/news
- type: Leadership
  url: https://www.upstage.ai/team/pr
- type: Blog
  url: https://www.upstage.ai/blog
- type: DomainSecurity
  url: security/upstage-ai-domain-security.yml
- type: Website
  url: https://upstage.ai
- type: Documentation
  url: https://console.upstage.ai/docs/getting-started
- type: APIReference
  url: https://console.upstage.ai/api/chat
- type: LLMsTxt
  url: https://console.upstage.ai/llms.txt
- type: RateLimits
  url: https://console.upstage.ai/docs/guides/rate-limits
- type: ErrorCodes
  url: https://console.upstage.ai/docs/resources/error-codes
- type: ChangeLog
  url: https://console.upstage.ai/docs/resources/changelog
- type: MCPServer
  name: MCP server manifest
  url: mcp/upstage-ai-mcp.yml
- type: MCPServer
  name: MCP server guide
  url: https://console.upstage.ai/docs/guides/mcp-server
- type: GitHubOrganization
  url: https://github.com/UpstageAI
- type: TermsOfService
  url: https://console.upstage.ai/docs/terms/terms-of-use
- type: PrivacyPolicy
  url: https://console.upstage.ai/docs/terms/privacy-policy
- type: SLA
  url: https://console.upstage.ai/docs/terms/sla
apis:
- aid: upstage-ai:chat-completions
  name: Upstage Chat Completions API
  description: POST /chat/completions for Solar models (OpenAI-compatible).
  humanURL: https://console.upstage.ai/api/chat
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/chat.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:responses
  name: Upstage Responses API
  description: OpenAI-compatible Responses API with structured outputs, tool calling, reasoning and file_search.
  humanURL: https://console.upstage.ai/api/responses
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/responses.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:embeddings
  name: Upstage Embeddings API
  description: Solar Embedding vectors for passages and queries.
  humanURL: https://console.upstage.ai/api/embeddings
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/embeddings.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:document-parse
  name: Upstage Document Parse API
  description: Parse documents into structured HTML or Markdown, sync and async.
  humanURL: https://console.upstage.ai/api/parse/document-parsing
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/parse/document-parsing.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:document-ocr
  name: Upstage Document OCR API
  description: OCR for scanned documents and images.
  humanURL: https://console.upstage.ai/api/parse/document-ocr
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/parse/document-ocr.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:information-extraction
  name: Upstage Universal Information Extraction API
  description: Schema-driven structured extraction from documents, with async and schema generation.
  humanURL: https://console.upstage.ai/api/information-extraction/universal-extraction
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/information-extraction/universal-extraction.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:document-classification
  name: Upstage Document Classification API
  description: Classify documents into user-defined classes.
  humanURL: https://console.upstage.ai/api/document-classification
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/document-classification.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:groundedness-check
  name: Upstage Groundedness Check API
  description: Check LLM answers against source context.
  humanURL: https://console.upstage.ai/api/groundedness-checking
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/groundedness-checking.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:translation
  name: Upstage Translation API
  description: Korean, English and Japanese translation models.
  humanURL: https://console.upstage.ai/api/translation
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/translation.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:vector-stores
  name: Upstage Vector Stores API
  description: Create, manage and search vector stores and file batches for file search.
  humanURL: https://console.upstage.ai/api/search/vector-stores/create-vector-store
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/search/vector-stores/create-vector-store.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:agents
  name: Upstage Agents API
  description: 'Run Studio document agents: upload files and create/retrieve jobs.'
  humanURL: https://console.upstage.ai/api/agents/jobs/create-job
  baseURL: https://api.upstage.ai/v1
  properties:
  - type: Documentation
    url: https://console.upstage.ai/api/agents/jobs/create-job.md
  x-note: Documented in the API reference; endpoint path/base not individually verified beyond the docs index; provider OpenAPI
    not publicly served.
- aid: upstage-ai:upstage-ai-system-one-api
  name: Upstage System One API
  description: The System One API from Upstage — 1 operation(s) for system one.
  humanURL: https://console.upstage.ai/api/systemone
  baseURL: https://api.upstage.ai/v1
  tags:
  - Systemone
  tags_raw:
  - System One
  properties:
  - type: OpenAPI
    url: openapi/upstage-ai-system-one-api-openapi.yml
  - type: Documentation
    url: https://console.upstage.ai/api/systemone.md
  - type: JSONSchema
    url: json-schema/upstage-ai-system-one-request-schema.json
  - type: JSONSchema
    url: json-schema/upstage-ai-system-one-response-schema.json
x-coverage:
  state: unreadable
  reason: no-machine-readable-spec
  method: derived
  generated: '2026-10-12'
  generator: derive-coverage.py (pre-flight evidence)
  detail: the company publishes developer documentation but serves no machine-readable contract from it
  evidence:
  - url: https://solar-chat.upstage.ai/mcp
    status: 403
  - url: https://upstage.ai
    status: 200
x-enrichment:
  date: '2026-10-12'
  status: enriched
  artifacts_added: 20
  pass: local-v5

Upstage API — frequently asked questions

Does Upstage have an API?

Yes. APIs.io lists 12 APIs from Upstage, including Upstage Chat Completions API, Upstage Responses API and Upstage Embeddings API, and 9 more.

Is there an OpenAPI specification for the Upstage API?

Yes. APIs.io indexes 1 OpenAPI specification for Upstage, each linked for download from this page.

How do I authenticate with the Upstage API?

Upstage uses bearer-token authentication (1 scheme). The details are profiled on APIs.io as Upstage Ai Authentication.

Does Upstage have an MCP server?

Yes. APIs.io lists 2 MCP servers for Upstage: MCP server requiring an API key; 2 tools listed.

Is the Upstage API ready for AI agents?

Upstage has a Kin Score of 34.7 out of 100 (thin) and an Agent Readiness score of 24.3 (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/upstage-ai"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/upstage-ai/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.