Jamba Mini 1.7 - smaller and efficient version with improved grounding and instruction following. Perfect for cost-effective tasks while maintaining 256k context window.
Added Jul 9, 2025
Context Window
256.0K
Max Output
4.1K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.41/1M
Cache Read (Auto)
$0.099/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
2.3
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
32.2%
Better than 9% of models compared
HLE
Humanity's Last Exam
4.4%
Better than 23% of models compared
IFBench
Instruction-following benchmark
31.4%
Better than 16% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
12.6%
Better than 10% of models compared
AA-LCR
Long context reasoning evaluation
15.3%
Better than 23% of models compared
Coding
SciCode
Python programming for scientific computing
9.3%
Better than 9% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
0.0%
Better than 5% of models compared
LiveCodeBench
Contamination-free coding benchmark
6.1%
Better than 4% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
0.3%
Better than 2% of models compared
AIME
American Invitational Mathematics Examination
1.3%
Better than 11% of models compared
Math-500
Diverse mathematical problem solving benchmark
25.8%
Better than 3% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
38.8%
Better than 7% of models compared
Last updated Aug 16, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Jamba Mini with similar models from the same provider or model family.
Jamba Mini 1.7
jamba-mini-1.7Latest smaller Jamba model (52B params) with improved grounding and instruction following. Cost-effective option for smaller tasks while maintaining the 256k context window.
Jamba Mini 1.6
jamba-mini-1.6Smaller and cheaper version of Jamba Large 1.6 (52B parameters versus 398B parameters), ideal for smaller tasks and lower budgets, still with a 256k context window.
Jamba Large
jamba-largeJamba 1.7 with improved grounding and instruction following for more accurate and reliable responses. Ideal for complex reasoning and document analysis tasks with 256k context window.
Jamba Large 1.7
jamba-large-1.7Latest Jamba model with improved grounding and instruction following for more accurate and reliable responses. Superior speed while processing large volumes of unstructured data.
Jamba Large 1.6
jamba-large-1.6Its ability to process large volumes of unstructured data (256k tokens) with high accuracy makes it ideal for summarization and document analysis.
AionLabs: Aion 3.0 Mini
aion-labs/aion-3.0-miniAion 3.0 Mini is a DeepSeek-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.