Jamba 1.5 Large
AI21's hybrid Mamba/Transformer model — unique state-space architecture for long context at low memory.
Pricing
Input$2 / 1M
Output$8 / 1M
Hybrid Mamba/Transformer SSM architecture.
Cost bandBalanced
Free tierTrial credits available.
Limits
Context window256k
Max output4,096
Knowledge cutoffMar 2024
DeploymentAI21 API, Azure AI, Bedrock, SambaNova
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forLong-document processing, RAG over very large corpora, and cost-efficient 256k context workloads.
Business fitArchitecturally distinct: worth evaluating when Transformer-based models are cost-prohibitive at long context.
Capabilities
Hybrid SSM/TransformerLong contextFunction calling
Benchmark scores
Composite71 / 100
Coding64 / 100 (HumanEval)
Reasoning72 / 100 (MMLU-Pro)
Long context84 / 100 (RULER 256K)
Instruction following74 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Oct 1, 2024. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJan 10, 2026
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.