AI21 Labs

Use the AI21 Labs API to call Jamba models such as jamba-mini and jamba-large.

API Key

To use AI21 Labs, you need to set the AI21_API_KEY environment variable, or specify the apiKey in the provider configuration.

Example of setting the environment variable:

export AI21_API_KEY=your_api_key_here

Model Selection

You can specify which AI21 model to use in your configuration. The public aliases are:

1. jamba-mini
2. jamba-large

The provider also recognizes the versioned IDs jamba-mini-2, jamba-mini-2-2026-01, jamba-large-1.7, and jamba-large-1.7-2025-07.

To compare the two models:

providers:
  - ai21:jamba-mini
  - ai21:jamba-large

Options

The provider accepts these options:

• temperature: Controls the randomness of the output.
• top_p: Controls nucleus sampling, affecting the randomness of the output.
• max_tokens: The maximum length of the generated text.
• response_format: Set to { type: 'json_object' } for JSON output or { type: 'text' } for text output.
• apiKeyEnvar: An environment variable that contains the API key.
• apiBaseUrl: The base URL of the AI21 API.

Example Configuration

providers:
  - id: ai21:jamba-mini
    config:
      apiKey: your_api_key_here
      temperature: 0.1
      top_p: 1
      max_tokens: 1024
      response_format: { type: 'json_object' }

Cost

Promptfoo estimates cost using separate input and output rates. Check AI21's pricing and set your own rates if needed:

providers:
  - id: ai21:jamba-large
    config:
      inputCost: 0.000002 # Example: $2 per million input tokens
      outputCost: 0.000008 # Example: $8 per million output tokens

inputCost and outputCost are in USD per token. Use cost to apply the same rate to both.

Supported environment variables

These AI21-related environment variables are supported:

Variable	Description
AI21_API_BASE_URL	The base URL (protocol + hostname + port) to use for the AI21 API.
AI21_API_KEY	AI21 API key.