AI21 Labs

AI21 Labs is an enterprise foundation-model company best known for the Jamba family of open-weight hybrid Mamba/Transformer models and AI21 Maestro, a dynamic planning system that orchestrates tools, retrieval, and validated output during inference. The platform exposes a Bearer-token REST API at api.ai21.com covering chat completions, conversational RAG over a managed file library, batch processing, fine-tuning, and function calling. Official Python and TypeScript SDKs wrap the API with sync and async clients and integrate natively into LangChain and LlamaIndex. Jamba weights are also published on Hugging Face for self-hosted vLLM deployment.

AI21 Labs publishes 4 APIs on the APIs.io network, including AI21 Jamba Chat Completions API, Chat API, Library API, and 1 more. Tagged areas include Artificial Intelligence, Foundation Models, LLM, Jamba, and Mamba.

The AI21 Labs catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

AI21 Labs’ developer surface includes authentication, documentation, API reference, engineering blog, pricing, changelog, and 12 more developer resources.

🌐 Visit website 📡 Source on GitHub

43.1/100 developing ▬ flat Agent 21/100 agent aware open core · Apache-2.0 Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

AccessFreeSelf serve⚡ Free to try

1 APIs

Artificial Intelligence Foundation Models LLMJambaMambaRAG Agents Maestro Inference Enterprise AI Fine-Tuning

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 43.1/100 · developing

Contract Quality 12.0 / 20

Developer Ergonomics 5.0 / 16

Access Clarity 6.3 / 16

Operational Transparency 4.1 / 10

Contract Governance 1.1 / 10

Discoverability 6.1 / 8

Open Source Surface 5.0 / 10

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 21/100 · 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 0 / 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

Open Source Surface applies to this provider. This product is open source and we read its repository directly, so Open Source Surface carries 10 points of the composite. It is scored from what the repository actually publishes — a security policy, a contribution guide, a release history, a code of conduct — read live from the provider rather than inferred from our own catalog pointers. This facet adds; nothing was taken away to make room for it. An open-source project is not excused from the commercial facets, because exemption would strip it of the points it does earn. If we have the wrong repository, or this product is not open source, say so on your provider repo and we will drop the facet rather than have you publish against 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 80 points between them, because the conditional facet above carries the other 20. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 80% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

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 github.com/api-evangelist/ai21-labs: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 11

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

AI21 Jamba Chat Completions API

Conversational completions endpoint backed by the Jamba family of hybrid Mamba/Transformer models (Jamba 1.5 Mini, Jamba 1.5 Large, Jamba 1.6). Accepts a message array, system p...

AI21 Maestro API

Dynamic planning system that, at inference time, determines the optimal sequence of actions to solve a task. Exposes run creation and retrieval endpoints, supports validated out...

AI21 File Library API

Managed file storage for RAG workflows. Upload, list, retrieve, update, and delete documents that Maestro and Jamba endpoints can ground on at inference time.

AI21 Batch API

Asynchronous batch processing for large volumes of Jamba completions. Submit a batch job, poll for status, and download results when the run completes.

AI21 Fine-Tuning API

Fine-tuning service for Jamba models supporting full, LoRA, and QLoRA strategies. Create training jobs from uploaded datasets and deploy the resulting model variants behind the ...

AI21 Python SDK

Official Python SDK (ai21 on PyPI) wrapping the AI21 Studio REST API with sync and async clients, streaming support, LangChain / LlamaIndex integrations, and helpers for chat, M...

AI21 TypeScript / JavaScript SDK

Official TypeScript and JavaScript client for the AI21 Studio API, with typed request and response models and streaming helpers for browser and Node.js runtimes.

AI21 Jamba on Hugging Face

Open-weight releases of the Jamba family on Hugging Face for self-hosted inference via vLLM, Transformers, and other runtimes.

AI21 Labs Chat API

The Chat API from AI21 Labs — 1 operation(s) for chat.

AI21 Labs Library API

The Library API from AI21 Labs — 1 operation(s) for library.

AI21 Labs Maestro API

The Maestro API from AI21 Labs — 2 operation(s) for maestro.

Scroll for all 11

Open Collections 5

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

API Collection

OPEN COLLECTION

AI21 Studio Chat API

OPEN COLLECTION

AI21 Studio Chat Library API

OPEN COLLECTION

AI21 Studio Chat Maestro API

OPEN COLLECTION

AI21 Studio API

OPEN COLLECTION

GraphQL 1

GraphQL schemas published by this provider.

AI21 Labs GraphQL Schema

This conceptual GraphQL schema maps the AI21 Labs REST API surface — covering the Jamba chat completion, Maestro agentic planning, conversational RAG file library, batch process...

GRAPHQL

Pricing Plans 1

Published pricing tiers and plan structures.

Ai21 Labs Plans Pricing

1 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Ai21 Labs Rate Limits

2 limits

RATE LIMITS

FinOps 1

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

Ai21 Labs Finops

FINOPS

Event Specifications 1

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

AI21 Studio Streaming API

AsyncAPI description of AI21 Labs' documented streaming surface. The AI21 Studio Jamba chat completions endpoint streams partial responses over HTTP using Server-Sent Events (SS...

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

AI21 Labs API Rules

8 rules · 1 errors 7 warnings

SPECTRAL

Security Posture 2

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

Ai21 Labs Authentication

http · 1 scheme

SECURITY

Ai21 Labs Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

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

Ai21 Labs Agentic Access

5 operations · 3 acting

AGENTIC

Resources

Documentation 3

Reference material describing how the API behaves

ContributionGuide

ContributionGuide

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

LlmsText

LlmsText

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 3

Status, limits, changes, and where to get help

IssueTracker

IssueTracker

Releases

Releases

ChangeLog

ChangeLog

Commercial 2

Pricing, plans, and the legal terms of use

License

License

Pricing

Pricing

Company 3

The organization behind the API

Website

Website

Blog

Blog

LinkedIn

Other 2

Properties that don't map to a standard resource type

HuggingFace

HuggingFace

Source (apis.yml)

aid: ai21-labs
name: AI21 Labs
description: AI21 Labs is an enterprise foundation-model company best known for the Jamba family of open-weight hybrid Mamba/Transformer
  models and AI21 Maestro, a dynamic planning system that orchestrates tools, retrieval, and validated output during inference.
  The platform exposes a Bearer-token REST API at api.ai21.com covering chat completions, conversational RAG over a managed
  file library, batch processing, fine-tuning, and function calling. Official Python and TypeScript SDKs wrap the API with
  sync and async clients and integrate natively into LangChain and LlamaIndex. Jamba weights are also published on Hugging
  Face for self-hosted vLLM deployment.
type: Index
deliveryModel:
  model: open-core
  license: Apache-2.0
  open_source: true
  commercial: true
  callable_host: true
  label: Open core · an OSS project plus a commercial hosted product
  confidence: high
  source:
  - license
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: free
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Free · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/ai21-labs.png
tags:
- Artificial Intelligence
- Foundation Models
- LLM
- Jamba
- Mamba
- RAG
- Agents
- Maestro
- Inference
- Enterprise AI
- Fine-Tuning
tags_raw:
- AI
- Foundation Models
- LLM
- Jamba
- Mamba
- RAG
- Agents
- Maestro
- Inference
- Enterprise AI
- Fine-Tuning
url: https://raw.githubusercontent.com/api-evangelist/ai21-labs/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-29'
specificationVersion: '0.23'
apis:
- aid: ai21-labs:chat-completions
  name: AI21 Jamba Chat Completions API
  description: Conversational completions endpoint backed by the Jamba family of hybrid Mamba/Transformer models (Jamba 1.5
    Mini, Jamba 1.5 Large, Jamba 1.6). Accepts a message array, system prompts, temperature, max tokens, tools, and streaming,
    returning assistant messages with usage metadata.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Chat
  - Completions
  - Jamba
  - LLM
  properties:
  - type: Documentation
    url: https://docs.ai21.com/reference
  - type: AsyncAPI
    url: https://raw.githubusercontent.com/api-evangelist/ai21-labs/refs/heads/main/asyncapi/ai21-labs-asyncapi.yml
  - url: graphql/ai21-labs-graphql.md
    type: GraphQL
- aid: ai21-labs:maestro
  name: AI21 Maestro API
  description: Dynamic planning system that, at inference time, determines the optimal sequence of actions to solve a task.
    Exposes run creation and retrieval endpoints, supports validated output for strict instruction following, and orchestrates
    RAG, web search, file libraries, MCP tools, and custom HTTP tools.
  humanURL: https://docs.ai21.com/docs/maestro
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Maestro
  - Planning
  - Agents
  - Validated Output
  properties:
  - type: Documentation
    url: https://docs.ai21.com/docs/maestro
- aid: ai21-labs:library
  name: AI21 File Library API
  description: Managed file storage for RAG workflows. Upload, list, retrieve, update, and delete documents that Maestro and
    Jamba endpoints can ground on at inference time.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - File
  - RAG
  - Library
  - Documents
  tags_raw:
  - Files
  - RAG
  - Library
  - Documents
  properties:
  - type: Documentation
    url: https://docs.ai21.com/reference
- aid: ai21-labs:batch
  name: AI21 Batch API
  description: Asynchronous batch processing for large volumes of Jamba completions. Submit a batch job, poll for status,
    and download results when the run completes.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Batch
  - Async
  - Inference
  properties:
  - type: Documentation
    url: https://docs.ai21.com/reference
- aid: ai21-labs:fine-tuning
  name: AI21 Fine-Tuning API
  description: Fine-tuning service for Jamba models supporting full, LoRA, and QLoRA strategies. Create training jobs from
    uploaded datasets and deploy the resulting model variants behind the standard chat completions endpoint.
  humanURL: https://docs.ai21.com/docs/fine-tuning
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Fine-Tuning
  - LoRA
  - QLoRA
  - Training
  properties:
  - type: Documentation
    url: https://docs.ai21.com/docs/fine-tuning
- aid: ai21-labs:python-sdk
  name: AI21 Python SDK
  description: Official Python SDK (ai21 on PyPI) wrapping the AI21 Studio REST API with sync and async clients, streaming
    support, LangChain / LlamaIndex integrations, and helpers for chat, Maestro, library, and batch.
  humanURL: https://github.com/AI21Labs/ai21-python
  baseURL: https://github.com/AI21Labs/ai21-python
  tags:
  - SDK
  - Python
  - PyPI
  properties:
  - type: Repository
    url: https://github.com/AI21Labs/ai21-python
- aid: ai21-labs:typescript-sdk
  name: AI21 TypeScript / JavaScript SDK
  description: Official TypeScript and JavaScript client for the AI21 Studio API, with typed request and response models and
    streaming helpers for browser and Node.js runtimes.
  humanURL: https://github.com/AI21Labs/ai21-typescript
  baseURL: https://github.com/AI21Labs/ai21-typescript
  tags:
  - SDK
  - TypeScript
  - JavaScript
  properties:
  - type: Repository
    url: https://github.com/AI21Labs
- aid: ai21-labs:huggingface
  name: AI21 Jamba on Hugging Face
  description: Open-weight releases of the Jamba family on Hugging Face for self-hosted inference via vLLM, Transformers,
    and other runtimes.
  humanURL: https://huggingface.co/ai21labs
  baseURL: https://huggingface.co/ai21labs
  tags:
  - Hugging Face
  - Open Weights
  - Jamba
  - Self-Hosted
  properties:
  - type: Repository
    url: https://huggingface.co/ai21labs
- aid: ai21-labs:ai21-labs-chat-api
  name: AI21 Labs Chat API
  description: The Chat API from AI21 Labs — 1 operation(s) for chat.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/ai21-labs-chat-api-openapi.yml
- aid: ai21-labs:ai21-labs-library-api
  name: AI21 Labs Library API
  description: The Library API from AI21 Labs — 1 operation(s) for library.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Library
  properties:
  - type: OpenAPI
    url: openapi/ai21-labs-library-api-openapi.yml
- aid: ai21-labs:ai21-labs-maestro-api
  name: AI21 Labs Maestro API
  description: The Maestro API from AI21 Labs — 2 operation(s) for maestro.
  humanURL: https://docs.ai21.com/reference
  baseURL: https://api.ai21.com/studio/v1
  tags:
  - Maestro
  properties:
  - type: OpenAPI
    url: openapi/ai21-labs-maestro-api-openapi.yml
common:
- type: IssueTracker
  url: https://github.com/AI21Labs/ai21-python/issues
- type: Releases
  url: https://github.com/AI21Labs/ai21-python/releases
- type: ContributionGuide
  url: https://github.com/AI21Labs/ai21-python/blob/main/CONTRIBUTING.md
- type: License
  name: Apache-2.0
  url: https://github.com/AI21Labs/ai21-python/blob/main/LICENSE
- type: AgenticAccess
  url: agentic-access/ai21-labs-agentic-access.yml
- type: DomainSecurity
  url: security/ai21-labs-domain-security.yml
- type: Authentication
  url: authentication/ai21-labs-authentication.yml
- type: Website
  url: https://www.ai21.com/
- type: Documentation
  url: https://docs.ai21.com/
- type: APIReference
  url: https://docs.ai21.com/reference
- type: GitHubOrganization
  url: https://github.com/AI21Labs
- type: HuggingFace
  url: https://huggingface.co/ai21labs
- type: Blog
  url: https://www.ai21.com/blog/
- type: Pricing
  url: https://www.ai21.com/pricing/
- type: ChangeLog
  url: https://docs.ai21.com/changelog
- type: LinkedIn
  url: https://www.linkedin.com/company/ai21/
- type: X
  url: https://x.com/AI21Labs
- type: LlmsText
  url: https://docs.ai21.com/llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

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/ai21-labs"

All providers

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

Every operation they expose

curl "https://apis.io/api/v1/providers/ai21-labs/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/ai21-labs/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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.