ai21

library4.3.0pypypi✓ verified 47d ago

Official Python SDK for AI21 Labs API. Provides access to Jamba models (chat completions, streaming) and legacy J2 Jurassic models (completions). Current version: 4.3.0 (Mar 2026). SDK has two distinct API surfaces — modern Jamba chat completions API and legacy J2/Jurassic API — with different ChatMessage signatures. Jamba models are current; J2 models are legacy.

llm-agents ai-ml http-networking

pip install ai21

package ↗homepage ↗

Install & Compatibility

Where this runs

tested against v4.3.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.925 runs

installs and imports cleanly · install 0.0s · import 1.055s · 33MB

glibc

py 3.10–3.925 runs

installs and imports cleanly · install 4.0s · import 0.982s · 33MB

31MB installed

● package 31MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

AI21Client

✓ from ai21 import AI21Client

✗ from ai21 import AI21Client

ChatMessage

✓ from ai21 import ChatMessage

✗ from ai21.models.chat import ChatMessage

Minimal AI21 Jamba chat completion using ai21 SDK 4.x.

# pip install ai21 from ai21 import AI21Client from ai21.models.chat import ChatMessage import os client = AI21Client() # reads AI21_API_KEY env var response = client.chat.completions.create( model='jamba-large', messages=[ ChatMessage(content='You are a helpful assistant.', role='system'), ChatMessage(content='Explain large language models briefly.', role='user') ], max_tokens=150, temperature=0.7 ) print(response.choices[0].message.content)

Debug

Known issues

breakingTwo ChatMessage classes exist: ai21.models.chat.ChatMessage (Jamba, uses content=) and ai21.models.ChatMessage (J2/legacy, uses text= and RoleType). Mixing them causes TypeError.

fix

For Jamba models use: from ai21.models.chat import ChatMessage with content= and string roles. For J2 legacy: from ai21.models import ChatMessage with text= and RoleType.

affects: >= 2.0

breakingOld J2/Jurassic API uses client.chat.create() with system= as separate param. New Jamba API uses client.chat.completions.create() with system message inside messages list. Completely different method name.

fix

For Jamba: client.chat.completions.create(messages=[...]). For J2: client.chat.create(system=..., messages=[...]).

affects: >= 2.0

gotchaLLMs trained pre-2024 have no knowledge of Jamba models. Will generate J2 Jurassic patterns (model='j2-ultra', RoleType, text= parameter) which are legacy and will be deprecated.

fix

Use Jamba models: 'jamba-large', 'jamba-mini'. Use content= not text=. Use string roles not RoleType enum.

affects: all

gotchaAPI key env var is AI21_API_KEY. SDK reads it automatically if not passed explicitly to AI21Client().

fix

export AI21_API_KEY=your_key or pass api_key= to AI21Client().

affects: all

deprecatedJ2 Jurassic models (j2-ultra, j2-mid, j2-light) are legacy. Jamba is the current model family. New features only on Jamba.

fix

Migrate to jamba-large or jamba-mini for new projects.

affects: all

Upgrade

Version history

4.3.0latest on PyPI

Audit

Dependencies

httpxrequiredHTTP client. Installed automatically.

Agent activity

103 hits · last 30 days

node

seranking-bot

Amazon

petalbot

ahrefsbot

bytedance

amazonbot

Google (AI)

OpenAI (training)

Resources

packagehttps://pypi.org/project/ai21/ ↗

homepagehttps://www.ai21.com ↗