DeepSeek

DeepSeek is an artificial intelligence company that provides advanced large language models accessible through an API that is compatible with the OpenAI and Anthropic SDKs. The DeepSeek API offers chat completions, fill-in-the-middle completions, function calling, JSON output, streaming, multi-turn conversations, context caching, and a thinking/reasoning mode for complex problem solving.

DeepSeek publishes 4 API contracts indexed on the APIs.io network, including Completions API, Models API, User API, and 1 more. Tagged areas include Artificial Intelligence, Chat, Chat Completions, LLM, and Reasoning.

The DeepSeek catalog on APIs.io includes 1 event-driven AsyncAPI specification, 1 JSON-LD context, and 5 Spectral governance rulesets.

DeepSeek’s developer surface includes engineering blog, authentication, documentation, pricing, FAQ, changelog, and 16 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

43.3/100 developing ▬ flat Agent 23/100 agent aware Front door AI 3/6 light Heartbeat 100/100 alive saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessPaid

4 published contracts

Artificial Intelligence Chat Chat Completions LLM Reasoning Code Completion Foundation Models

What this lets a business do 1

Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →

AI Model Services

AE-110

Chat CompletionsCompletions

POST /chat/completions POST /completions

Kin Score

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

Composite quality — 43.3/100 · developing

Contract Quality 10.7 / 19

Developer Ergonomics 3.6 / 15

Access Clarity 6.7 / 15

Operational Transparency 3.9 / 10

Contract Governance 2.3 / 9

Discoverability 5.4 / 8

Regulatory Posture 3.4 / 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 6 / 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 0 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the AI & Biometrics 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/deepseek/"><img src="https://apis.io/badge/deepseek/card.svg" alt="DeepSeek 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)

8 more unmet checks in the Agent Readiness table above.

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

Developer Ergonomics scores 23.8 — up to +15.2 composite points
Access Clarity scores 44.7 — up to +11.1 composite points
Contract Quality scores 57.2 — up to +10.7 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/deepseek/apis.yml: open an issue on github.com/api-evangelist/deepseek 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
AI Model Routing	covered	38.3	-	2
Agent Skills (SKILL.md packages)	covered	38.3	-	2
IDE Extension Marketplaces (JetBrains, VS Code, Open VSX, Docker Verified Publishers, PyPI orgs)	covered	38.3	-	2
Raycast Store Extensions (first-party publishers + community-wrapped products)	covered	38.3	-	2
Obsidian Community Plugins (third-party APIs the Obsidian plugin ecosystem integrates)	covered	38.3	-	2
IFTTT Services (service publishers)	covered	38.3	-	2
Hugging Face Hub Organisations	covered	38.3	-	2

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 reaches extended

declared — publishes a spec that declares them

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

OpenAPI

measured — observed by APIs.io (published)

APIs 4

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

DeepSeek Completions API

The Completions API from DeepSeek — 1 operation(s) for completions.

DeepSeek Models API

The Models API from DeepSeek — 1 operation(s) for models.

DeepSeek User API

The User API from DeepSeek — 1 operation(s) for user.

DeepSeek Chat Completions API

The Chat Completions API from DeepSeek — 1 operation(s) for chat completions.

Open Collections 8

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

DeepSeek Completion Chat API

OPEN COLLECTION

DeepSeek Chat Completion API

OPEN COLLECTION

DeepSeek Completion Chat Completions API

OPEN COLLECTION

DeepSeek FIM Completion

OPEN COLLECTION

DeepSeek Models API

OPEN COLLECTION

DeepSeek Completion Chat Models API

OPEN COLLECTION

DeepSeek Completion Chat User API

OPEN COLLECTION

DeepSeek User Balance API

OPEN COLLECTION

Scroll for all 8

DeepSeek API pricing

Not yet checked against DeepSeek's own pricing page. Compiled by API Evangelist on 2026-05-05 from api-docs.deepseek.com/quick_start/pricing; confirm before you rely on a figure.

Plan	Price
DeepSeek-V4-Flash usage-based	$0.0028 per 1M input tokens (cache hit) · $0.14 per 1M input tokens (cache miss)
DeepSeek-V4-Pro usage-based	$0.003625 per 1M input tokens (cache hit) · $0.435 per 1M input tokens (cache miss)

Plan details, limits and sources →

Rate limits

Dynamic concurrency cap: dynamic — varies with current server load concurrent requests
Inference connection timeout: 600 seconds to first token

Compiled by API Evangelist, not yet checked against DeepSeek's documentation. Rate-limit details →

Billed by: token · FinOps profile →

Pricing Plans 1

Published pricing tiers and plan structures.

Deepseek Plans Pricing

2 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Deepseek Rate Limits

2 limits

RATE LIMITS

Service Levels 1

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

DeepSeek

SLA

FinOps 1

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

Deepseek Finops

FINOPS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

DeepSeek Streaming API (HTTP + SSE)

AsyncAPI definition for the streaming surface of the DeepSeek API. DeepSeek exposes an OpenAI-compatible HTTP API. When the `stream` request parameter is set to `true`, the serv...

ASYNCAPI

Semantic Vocabularies 1

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

Deepseek Context

6 classes · 9 properties

JSON-LD

Spectral Rules 5

Spectral governance rulesets for linting and validating these APIs.

DeepSeek — asyncapi rules

8 rules · 1 errors 7 warnings

SPECTRAL

DeepSeek — chat completion api rules

4 rules · 1 errors 3 warnings

SPECTRAL

DeepSeek — fim completion rules

3 rules · 1 errors 2 warnings

SPECTRAL

DeepSeek — lists models api rules

3 rules · 1 errors 2 warnings

SPECTRAL

DeepSeek — user balance api rules

3 rules · 1 errors 2 warnings

SPECTRAL

Security Posture 2

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

Deepseek Authentication

http · 1 scheme

SECURITY

Deepseek Domain Security

TLSv1.3 · DMARC

SECURITY

Agentic Access 1

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

Deepseek Agentic Access

4 operations · 2 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

Design & Contract 3

Pagination, idempotency, versioning, errors, and events

ErrorCodes

ErrorCodes

JSONLD

JSONLD

Vocabulary

Vocabulary

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Authentication

Authentication

Operate 4

Status, limits, changes, and where to get help

RateLimits

StatusPage

FAQ

ChangeLog

Commercial 5

Pricing, plans, and the legal terms of use

Plans

FinOps

Pricing

PrivacyPolicy

TermsOfService

Company 3

The organization behind the API

Blog

Blog

LinkedIn

Website

Website

Other 1

Properties that don't map to a standard resource type

CapabilityMap

CapabilityMap

Source (apis.yml)

aid: deepseek
name: DeepSeek
url: https://raw.githubusercontent.com/api-evangelist/deepseek/refs/heads/main/apis.yml
description: DeepSeek is an artificial intelligence company that provides advanced large language models accessible through
  an API that is compatible with the OpenAI and Anthropic SDKs. The DeepSeek API offers chat completions, fill-in-the-middle
  completions, function calling, JSON output, streaming, multi-turn conversations, context caching, and a thinking/reasoning
  mode for complex problem solving.
kind: company
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: paid
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Paid
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-11-06'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/deepseek.png
access: 3rd-Party
position: Consuming
specificationVersion: '0.23'
x-docs-platform: docusaurus
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-09-25
tags:
- Artificial Intelligence
- Chat
- Chat Completions
- LLM
- Reasoning
- Code Completion
- Foundation Models
tags_raw:
- AI
- Artificial Intelligence
- Chat
- Chat Completion
- LLM
- Large Language Models
- Reasoning
- Code Completion
- Foundation Models
created: '2025-01-27'
modified: '2026-10-06'
apis:
- aid: deepseek:deepseek-completions-api
  name: DeepSeek Completions API
  description: The Completions API from DeepSeek — 1 operation(s) for completions.
  humanURL: https://api-docs.deepseek.com/api/create-chat-completion
  baseURL: https://api.deepseek.com
  tags:
  - Completions
  properties:
  - type: OpenAPI
    url: openapi/deepseek-completions-api-openapi.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/create-chat-completion
  - type: AsyncAPI
    url: asyncapi/deepseek-asyncapi.yml
  - type: Rules
    url: rules/deepseek-chat-completion-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/guides/fim_completion
  - type: Rules
    url: rules/deepseek-fim-completion-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/list-models
  - type: Rules
    url: rules/deepseek-lists-models-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/get-user-balance
  - type: Rules
    url: rules/deepseek-user-balance-api-rules.yml
- aid: deepseek:deepseek-models-api
  name: DeepSeek Models API
  description: The Models API from DeepSeek — 1 operation(s) for models.
  humanURL: https://api-docs.deepseek.com/api/create-chat-completion
  baseURL: https://api.deepseek.com
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/deepseek-models-api-openapi.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/create-chat-completion
  - type: AsyncAPI
    url: asyncapi/deepseek-asyncapi.yml
  - type: Rules
    url: rules/deepseek-chat-completion-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/guides/fim_completion
  - type: Rules
    url: rules/deepseek-fim-completion-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/list-models
  - type: Rules
    url: rules/deepseek-lists-models-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/get-user-balance
  - type: Rules
    url: rules/deepseek-user-balance-api-rules.yml
- aid: deepseek:deepseek-user-api
  name: DeepSeek User API
  description: The User API from DeepSeek — 1 operation(s) for user.
  humanURL: https://api-docs.deepseek.com/api/create-chat-completion
  baseURL: https://api.deepseek.com
  tags:
  - User
  properties:
  - type: OpenAPI
    url: openapi/deepseek-user-api-openapi.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/create-chat-completion
  - type: AsyncAPI
    url: asyncapi/deepseek-asyncapi.yml
  - type: Rules
    url: rules/deepseek-chat-completion-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/guides/fim_completion
  - type: Rules
    url: rules/deepseek-fim-completion-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/list-models
  - type: Rules
    url: rules/deepseek-lists-models-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/get-user-balance
  - type: Rules
    url: rules/deepseek-user-balance-api-rules.yml
- aid: deepseek:deepseek-chat-completions-api
  name: DeepSeek Chat Completions API
  description: The Chat Completions API from DeepSeek — 1 operation(s) for chat completions.
  humanURL: https://api-docs.deepseek.com/api/create-chat-completion
  baseURL: https://api.deepseek.com
  tags:
  - Chat Completions
  properties:
  - type: OpenAPI
    url: openapi/deepseek-chat-completions-api-openapi.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/create-chat-completion
  - type: AsyncAPI
    url: asyncapi/deepseek-asyncapi.yml
  - type: Rules
    url: rules/deepseek-chat-completion-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/guides/fim_completion
  - type: Rules
    url: rules/deepseek-fim-completion-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/list-models
  - type: Rules
    url: rules/deepseek-lists-models-api-rules.yml
  - type: Documentation
    url: https://api-docs.deepseek.com/api/get-user-balance
  - type: Rules
    url: rules/deepseek-user-balance-api-rules.yml
common:
- type: CapabilityMap
  url: capabilities/deepseek-capability-edges.yml
  name: DeepSeek Business Capability Map
- type: Plans
  url: plans/deepseek-plans-pricing.yml
- type: FinOps
  url: finops/deepseek-finops.yml
- url: https://www.deepseek.com/news/
  type: Blog
- type: AgenticAccess
  url: agentic-access/deepseek-agentic-access.yml
- type: DomainSecurity
  url: security/deepseek-domain-security.yml
- type: Authentication
  url: authentication/deepseek-authentication.yml
- type: GitHubOrganization
  url: https://github.com/deepseek-ai
- type: LinkedIn
  url: https://www.linkedin.com/company/deepseek-ai
- type: Documentation
  url: https://api-docs.deepseek.com/
- type: Pricing
  url: https://api-docs.deepseek.com/quick_start/pricing
- type: Authentication
  url: https://api-docs.deepseek.com/quick_start/token_usage
- type: RateLimits
  url: https://api-docs.deepseek.com/quick_start/rate_limit
- type: ErrorCodes
  url: https://api-docs.deepseek.com/quick_start/error_codes
- type: StatusPage
  url: https://status.deepseek.com/
- type: FAQ
  url: https://api-docs.deepseek.com/faq
- type: ChangeLog
  url: https://api-docs.deepseek.com/updates
- type: Website
  url: https://www.deepseek.com/
- type: PrivacyPolicy
  url: https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html
- type: TermsOfService
  url: https://chat.deepseek.com/downloads/DeepSeek%20Terms%20of%20Use.html
- type: JSONLD
  url: json-ld/deepseek-context.jsonld
- type: Vocabulary
  url: vocabulary/deepseek-vocabulary.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

DeepSeek API — frequently asked questions

Does DeepSeek have an API?

Yes. APIs.io lists 4 APIs from DeepSeek, including DeepSeek Completions API, DeepSeek Models API and DeepSeek User API, and 1 more.

Is there an OpenAPI specification for the DeepSeek API?

Yes. APIs.io indexes 4 OpenAPI specifications for DeepSeek, each linked for download from this page.

How do I authenticate with the DeepSeek API?

DeepSeek uses bearer-token authentication (http · 1 scheme). The details are profiled on APIs.io as Deepseek Authentication.

How much does the DeepSeek API cost?

APIs.io lists 2 pricing plans for DeepSeek, with each plan's price, limits and inclusions under Pricing on this page.

Is the DeepSeek API ready for AI agents?

DeepSeek has a Kin Score of 43.3 out of 100 (developing) and an Agent Readiness score of 22.9 (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/deepseek"

All providers

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

Every operation they expose

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

How their score was established

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