modelgrep
A

AI21: Jamba Large 1.7

ai21/jamba-large-1.7

163rd smartest of 178ToolsJSON
Use via OpenRouter ↗
Intelligence
10.9
163rd of 178
Design Elo
Speed
5
288th fastest
Latency
563ms
first token
Input price
$2.00
244th cheapest
Context
256K
4K max out

How it compares

Smarter than8%
of all ranked models
Faster than2%
of all ranked models
Cheaper than18%
of all ranked models

Overview

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...

Benchmarks

independent · via OpenRouter
Artificial Analysis10th percentile
Intelligence Index
10.9
Coding Index
7.8
Agentic Index
4.5
GPQA Diamond
39%
Humanity's Last Exam
4%
SciCode
19%
Tau²-Bench (agentic)
14%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
AI21fp8$2.00$8.00100%

Specifications

Context window256K
Max output4K
Knowledge cutoffAug 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Jamba Large 1.7 FAQ

How much does Jamba Large 1.7 cost?

Jamba Large 1.7 costs $2.00 per million input tokens and $8.00 per million output tokens via OpenRouter, making it 244th cheapest of 298 paid models.

How smart is Jamba Large 1.7?

Jamba Large 1.7 scores 10.9 on the Artificial Analysis Intelligence Index, ranking 163rd of 178 benchmarked models, with a GPQA Diamond score of 39%.

How fast is Jamba Large 1.7?

Jamba Large 1.7 generates around 5 tokens per second with 563ms time-to-first-token (p50), the 288th fastest tracked model.

What is Jamba Large 1.7's context window?

Jamba Large 1.7 supports a 256K-token context window and can output up to 4K tokens. It accepts text input.

Compare head-to-head