Last verified
RETIRED FEB 1 2026256K CONTEXTTEXTSSM-TRANSFORMERNO CACHE ROW

Jamba Mini 1.7 API Pricing

Jamba Mini 1.7 was retired by AI21 Labs on February 1, 2026 - the jamba-mini-1.7 model id no longer answers. Its last listed rates were $0.20/M input and $0.40/M output, kept here for invoice checks and migration math. Checked against AI21's Jamba model-deprecation table.

Input - per 1M tokens
$0.20/M
Source AI21 Studio public list
Output - per 1M tokens
$0.40/M
Context 256K public list
Cache N/A
$0.20/M
Cache no public row not listed
Effective - agentic blend
$0.216/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Jamba Mini 1.7 public token rates. AI21 does not publish a separate prompt-cache token rate for this model.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

LONG DOC ANALYSIS

Reading 100-page contracts

$0.039/doc
180k in / 8k out~2,551 docs/$100
CODING AGENT

Codebase-scale migration

$0.028/task
120k in / 10k out~3,571 tasks/$100
RAG - SUPPORT

Ticket triage

$0.002/ticket
8k in / 1k out~50,000 tickets/$100
ASSISTANT

Research planning turn

$0.0044/turn
18k in / 2k out~22,727 turns/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

What's a token →
Estimate · jamba-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 516
Words 82
Tokens (estimated) 134 tokens
Cost as input · uncached $0.00003 USD
Cost as output · uncached $0.00005 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Jamba Mini 1.7 Current $0.20 $0.40 $0.216 agentic 92/8 256K High-volume long-context work
Jamba Large 1.7 $2.00 $8.00 $2.48 +11× 256K Long-document RAG and analysis
Mistral Small 4 $0.15 cache $0.015 $0.60 $0.0842 −2.6× 256K Cheap open small model
Gemini 3.5 Flash-Lite $0.30 cache $0.03 $2.50 $0.272 +26% 1M Google's low-cost multimodal tier
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −30% 1M Bulk low-cost traffic

Frequently asked.

Practical Jamba Mini 1.7 pricing questions, with AI21's published rates kept separate from workload assumptions.

Q · 01 Can I still call Jamba Mini 1.7? +
No. AI21 Labs retired jamba-mini-1.7 on February 1, 2026, and requests to it now fail. The rates on this page are the last ones AI21 Labs listed, kept for reading old invoices and for estimating a migration.
Q · 02 What is Jamba Mini 1.7 priced at? +
On AI21 Studio it lists $0.20/M input and $0.40/M output, with a 256K-token context - the same window as Jamba Large. Verified on the AI21 pricing page 2026-07-11.
Q · 03 Does Jamba Mini really have a 256K context? +
Yes. Both Jamba Mini and Jamba Large share the 256K-token context. Jamba's hybrid SSM-Transformer design keeps long contexts affordable, which is why Mini can offer the same window at a fraction of Large's price.
Q · 04 Is there a prompt-cache discount? +
No separate cache-read rate is published for Jamba Mini, so this calculator keeps cached input equal to base input ($0.20/M). The token-only blended cost is about $0.22/M.
Q · 05 How does it compare with Jamba Large? +
Jamba Large 1.7 is 10x the input price ($2/$8) for stronger reasoning. Mini is the better fit for high-volume long-context RAG, extraction and classification.
Q · 06 Which API model ID should I use? +
None - jamba-mini-1.7 was retired on February 1, 2026. AI21's jamba-mini alias now points to Jamba2 Mini (jamba-mini-2-2026-01), at the same $0.20/$0.40.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against ai21.com · Last verified Sep 24, 2026
Methodology Report a correction More by Y.V.