Baltor Get started

Models

Jamba Mini

By AI21 Labs. Unknown parameters, a context window of 256,000 tokens, licence Unknown.

Facts

Released
2026-01-01 the release date models.dev records models.dev, read
Licence
Unknown
Open weights
Yes models.dev records whether the weights are open models.dev, read
Parameters
Unknown
Active parameters
Unknown
Knowledge cutoff
2024-08-22 the knowledge cutoff models.dev records models.dev, read
Context window
  • 256,000 tokens the context limit models.dev records for the maker's own API models.dev, read
Longest output
  • 4,096 tokens the output limit models.dev records for the maker's own API models.dev, read
Tool calling
  • Yes models.dev records tool_call as true models.dev, read
Structured output
  • Yes models.dev records structured_output as true models.dev, read
Reasoning controls
  • No models.dev records reasoning as false models.dev, read
Inputs and outputs
text in, text out models.dev, read
Good for
No source names a use.

Prices

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
AI21 Labs0.200 USD0.400 USD256,000 older than 30 days; check the providermodels.dev, read

Run it on your own hardware

No source lists weight files or a parameter count for this model, so its memory needs are Unknown.

Use it from your harness

Set up for AI21 Labs with the model jamba-mini. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ai21": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AI21 Labs",
      "options": {
        "baseURL": "https://api.ai21.com/studio/v1",
        "apiKey": "{env:AI21_API_KEY}"
      },
      "models": {
        "jamba-mini": {
          "name": "Jamba Mini",
          "limit": {
            "context": 256000,
            "output": 4096
          }
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "ai21": {
      "baseUrl": "https://api.ai21.com/studio/v1",
      "api": "openai-completions",
      "apiKey": "$AI21_API_KEY",
      "models": [
        {
          "id": "jamba-mini"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and AI21 Labs documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and AI21 Labs documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

Two more publishers are linked, never copied, because their terms do not allow it:

  • Artificial Analysis publishes its own intelligence, speed and price measurements.
  • OpenRouter lists current prices and uptime for each provider it routes to.

Sources of this page