Jamba 1.5 Mini

Affordable 256K context model; uses SSM hybrid for efficient long-context processing.

Pricing

Model Overview

Tracked token-pricing fields for this model family. Empty pricing fields stay hidden until the source publishes them.

Surface

Input and output modalities, enabled feature flags, strengths, and tradeoffs.

Model capabilities
Attribute	Values
Modalities	text to text
Capabilities	batchSupportfunctionCallingstructuredOutputs
Strengths	Very cheap 256K context, Fast SSM processing
Tradeoffs	No vision, lower quality than Large

References

Canonical launch, documentation, pricing, and release-note URLs.

Official model links
Reference	URL
Intro	https://www.ai21.com/blog/announcing-jamba-1-5
Docs	https://docs.ai21.com/docs/jamba-models
Pricing	https://www.ai21.com/jamba
Release note	https://docs.ai21.com/changelog/

Coverage

Reported benchmark families, versions, scores, sources, and notes.

Benchmark coverage
Benchmark	Version	Score	Date	Source	Notes

Lifecycle

Lifecycle transitions and release timeline for this model family.

Release history
Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
Jamba 1.5 Mini	jamba-1-5-mini	Active	Sep 9, 2024	—	—	Current published model family snapshot.

Surfaces

Provider-specific hosting, context, pricing notes, feature differences, and provider-status context.

Host coverage
Host	Type	Context	Pricing Note	Differences
AI21 API	first-party	256.0K	$0.20/$0.40 per MTok.	—

Migration

Documented migration summary, successor families, and known breaking changes.

Migration guidance
Topic	Details
Summary	Lower-priced 256K context option in this catalog.
Replacement models	jamba-1-5-large

Timeline

Cataloged model-family updates and source references.

Change events
Date	Type	Title	Description	Source
Sep 9, 2024	family_added	Jamba 1.5 Mini published	Initial public model family launch.	Jamba 1.5 Mini release notes

From AI21 Labs