LiteLLMModels

J2 Ultra API Pricing

As of October 10, 2026, J2 Ultra costs $15.00 per 1M input tokens and $15.00 per 1M output tokens on AI21 Labs. Across 2 providers on LiteLLM, the input price ranges from $15.00 to $18.80. It has an 8,192-token context window and returns up to 8,192 tokens per response.

By AI21 LabsModel ID j2-ultraPrices updated Checked
Input
$15.00 / 1M tokens
Output
$15.00 / 1M tokens
Context window
8,192 tokens
Max output
8,192 tokens
Providers
2

J2 Ultra pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
AI21 Labsj2-ultra$15.00$15.008K
Amazon Bedrockai21.j2-ultra-v1$18.80$18.808K

What J2 Ultra costs in practice

1,000 requests with 2,000 input and 500 output tokens each

AI21 Labs$37.50
Amazon Bedrock$47.00

Use J2 Ultra with LiteLLM

Call J2 Ultra through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="j2-ultra",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: j2-ultra
    litellm_params:
      model: j2-ultra
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "j2-ultra",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

J2 Ultra FAQ

How much does J2 Ultra cost?

J2 Ultra costs $15.00 per 1M input tokens and $15.00 per 1M output tokens on AI21 Labs. Across 2 providers on LiteLLM, the input price ranges from $15.00 to $18.80.

What is the context window of J2 Ultra?

J2 Ultra has an 8,192-token context window and returns up to 8,192 tokens per response.

Which providers offer J2 Ultra?

J2 Ultra is available from 2 providers through LiteLLM: AI21 Labs and Amazon Bedrock. The lowest price is on AI21 Labs.

How do I call J2 Ultra with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="j2-ultra", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: AI21 Labs, Amazon Bedrock.

Provider pages: AI21 Labs, Amazon Bedrock.