Nova 2 Lite

nova-2-lite-v1

Nova 2 Lite is a fast, affordable reasoning model that works across text, images, and video to produce text outputs. It performs well on everyday tasks like document analysis, video understanding, information extraction, coding, grounded Q&A, and automating multi-step agent workflows.

Context: 1M tokens
Endpoint

Get API Key Compare

Pricing

Input$0.30 / 1M

Output$2.50 / 1M

Cache Write (5m)$0.30 / 1M

Cache Write (1h)$0.30 / 1M

Cache Read$0.30 / 1M

Web Search$0 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="nova-2-lite-v1",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="nova-2-lite-v1",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common7 params

modelmessagesmax_tokenstemperaturetop_pstreamtools

Extended4 params

reasoning_effortstream_optionsthinkingextra_body

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

nova-2-lite-v1

Compare with Other Models

See how this model compares to others from the same provider.

Nova Premier 1.0

Amazon Nova Premier is Amazon's most powerful multimodal model, designed for complex reasoning tasks and frequently used as a top-tier “teacher” model for distilling and training custom systems.

Context: 1M
Input: $3.13/M
Output: $15.63/M

Nova Lite 1.0

Context: 300K
Input: $0.18/M
Output: $0.72/M

Nova Micro 1.0

Context: 128K
Input: $0.105/M
Output: $0.42/M

Nova Pro 1.0

Context: 300K
Input: $2.40/M
Output: $9.60/M