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

Jamba 1.5 LargeDeprecated

AI21
Tool use
Context
256K
Max output
256K
Serving providers
3
Cheapest input
$2.00 /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
4.8
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
EvalComputeProxy22.2default
GPQA Diamond43%default
Humanity's Last Exam4%default
LiveCodeBench14%default
MMLU-Pro57%default
SciCode16%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon Bedrock$2.00$8.001
Ai21$2.00$8.001
Vertex AI Ai21 Models$2.00$8.001

Price history

input + output $/1M since we started tracking
Input Output
$0.000$2.00$4.00$6.00$8.00Aug 27Aug 30Jan 29Jun 22$8.00$2.00

Cost calculator

estimate your monthly spend on this model
$1,040
estimated / month

Model IDs

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

Frequently asked questions

Jamba 1.5 Large pricing, context and availability

Is Jamba 1.5 Large still available?

Jamba 1.5 Large 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 Large cost?

Jamba 1.5 Large's last-known pricing, before it was retired on 2026-11-26, was $2.00 per 1M input tokens and $8.00 per 1M output tokens.

What was the context window of Jamba 1.5 Large?

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

What could Jamba 1.5 Large do?

Jamba 1.5 Large 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