This model was retired on 2026-11-26. The pricing below is the last-known rate, kept for migration reference.

Jamba 1.5 MiniDeprecated

AI21
Tool use
Context
256K
Max output
256K
Serving providers
3
Cheapest input
$0.20 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Intelligence Index
2.3
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
EvalComputeProxy2.6default
GPQA Diamond30%default
Humanity's Last Exam5%default
LiveCodeBench6%default
MMLU-Pro37%default
SciCode8%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon Bedrock$0.20$0.401
Ai21$0.20$0.401
Vertex AI Ai21 Models$0.20$0.401

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300$0.400Aug 27Aug 30Jan 29Jun 22$0.400$0.200

Cost calculator

estimate your monthly spend on this model
$72
estimated / month

Model IDs

copy the exact identifier for your platform
ai21.jamba-1-5-mini-v1:0jamba-1.5-minivertex_ai/jamba-1.5-mini

Frequently asked questions

Jamba 1.5 Mini pricing, context and availability

Is Jamba 1.5 Mini still available?

Jamba 1.5 Mini was retired on 2026-11-26. The pricing on this page is the last-known rate, kept for migration reference.

How much did Jamba 1.5 Mini cost?

Jamba 1.5 Mini's last-known pricing, before it was retired on 2026-11-26, was $0.20 per 1M input tokens and $0.40 per 1M output tokens.

What was the context window of Jamba 1.5 Mini?

Jamba 1.5 Mini had a 256K token context window and could return up to 256K output tokens.

What could Jamba 1.5 Mini do?

Jamba 1.5 Mini supported tool use.

Other AI21 models

compare pricing across the AI21 lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI