AI21 Labs
Frontier

Jamba Instruct

Previous

Instruction-tuned Jamba, closed-weights AI21 hosted variant focused on enterprise summarisation and long documents.

Jamba Instruct is a frontier AI model from AI21 Labs. It costs $0.5000 per million input tokens and $0.7000 per million output tokens (blended $0.5600/M), with a 256,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.5000/M
per million input tokens
OUTPUT
$0.7000/M
per million output tokens
BLENDED 70/30
$0.5600/M
unchanged since 3 May
CONTEXT
256,000
tokens

Hand-maintained from AI21 Labs's published pricing; no check date on record.

What it is good at
  • 256K context
  • Enterprise hosting
  • Tuned for summarisation
Typical use cases
  • Long-document summarisation
  • Enterprise RAG via AI21 API

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from AI21 Labs

See all 5 →

Frequently asked questions

How much does Jamba Instruct cost?

Jamba Instruct costs $0.5000 per million input tokens and $0.7000 per million output tokens, for a blended reference rate of $0.5600 per million tokens.

What is Jamba Instruct's context window?

Jamba Instruct supports up to 256,000 tokens of context in a single request.

What is Jamba Instruct best for?

Jamba Instruct is well suited to 256K context, Enterprise hosting and Tuned for summarisation.

Who makes Jamba Instruct?

Jamba Instruct is developed and served by AI21 Labs.

Terms used on this page