Jamba 1.5 Large
Frontier
SSM/Transformer hybrid with 256K context. Cheaper to serve at long context than pure Transformer architectures.
Jamba 1.5 Large is a frontier AI model from AI21 Labs. It costs $2.000 per million input tokens and $8.000 per million output tokens (blended $3.800/M), with a 256,000-token context window.
INPUT
$2.000/M
per million input tokens
OUTPUT
$8.000/M
per million output tokens
CONTEXT
256,000
tokens
What it is good at
- 256K context
- Cheap at long context
- Novel architecture
Typical use cases
- Long-document summarisation
- Architecture research
Benchmarks
vs. best public score
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from AI21 Labs
See all 5 →Frequently asked questions
How much does Jamba 1.5 Large cost?
Jamba 1.5 Large costs $2.000 per million input tokens and $8.000 per million output tokens, for a blended reference rate of $3.800 per million tokens.
What is Jamba 1.5 Large's context window?
Jamba 1.5 Large supports up to 256,000 tokens of context in a single request.
What is Jamba 1.5 Large best for?
Jamba 1.5 Large is well suited to 256K context, Cheap at long context and Novel architecture.
Who makes Jamba 1.5 Large?
Jamba 1.5 Large is developed and served by AI21 Labs.