Amazon Nova 2 Lite

amazon/nova-2-lite-v1

Run Amazon Nova 2 Lite in a hosted Python Task with extended thinking and file inputs.

Amazon's Nova 2 Lite model via OpenRouter. Multimodal model supporting text, image, video, and file inputs. Excels at document processing, video information extraction, code generation, and multi-step agentic workflows. Features 1M token context window.

What Amazon Nova 2 Lite supports in qbash

Extended thinkingReasons through a problem before it replies.
Image inputReads WEBP, PNG, JPEG and GIF images.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.

What is qbash?

qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Amazon Nova 2 Lite only at the ones that need judgment, with integrations, memory and files available in the same script.

A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.

How Tasks work

Specifications

Context window: 1Mtokens
Max output: 8,192tokens
Temperature: 0 to 1default 1

Use Amazon Nova 2 Lite in a Python Task

qbash.ai.raw calls Amazon Nova 2 Lite from a Task and returns its reply as a string.

main.py
notes = qbash.inputs.get("notes")

summary = qbash.ai.raw(
    f"Summarize these meeting notes in five bullets:\n\n{notes}",
    model="amazon/nova-2-lite-v1",
    system="You are a concise analyst.",
)

qbash.output({"summary": summary})

Model calls in Tasks

Extended thinking with Amazon Nova 2 Lite

Turn on Thinking in the same Settings popover to have Amazon Nova 2 Lite reason through a problem before it replies.