Skip to navigation
Authors and ModelsAmazon

Nova Lite 2

Nova Lite 2
Amazon · Text Generation
POST /v1/chat/completions

Fast, cost-effective multimodal reasoning model for text, images, documents, and video on a 1M context (long docs and ~90 min clips).

At a glance

FieldValue
Model idnova-lite-2
Model release date2025-12-02
Input modalitiesText, Image, Video, Document
Output modalitiesText
Context window1M
Weight precision-
Max output tokens131,072
Featuresvision, function_calling, reasoning
Native inferenceNo
NewNo
Structured outputNot supported
Batch API35% off list price
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/nova-lite-2:generateContent
Alternate model idsamazon-nova-lite-2, amazon/nova-lite-2, us.amazon.nova-2-lite-v1:0

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.38
Outputper 1M generated tokens$3.16
Cached inputper 1M tokens$0.2128
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "nova-lite-2", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature, from 0 (deterministic) to 1. Not available with reasoning_effort high. · Range: 0 – 1
top_pnumberno0.9Nucleus sampling probability mass. Lower = more focused. Not available with reasoning_effort high. · Range: 0 – 1
max_tokensnumberno60000Maximum tokens in the response. Not available with reasoning_effort high. · Range: 1 – 65535
stopstringno-Up to 4 strings where the model will stop generating further tokens.
enable_thinkingbooleannotrueEnable extended reasoning before the final answer. A request that forces a tool call runs without reasoning unless it sets enable_thinking.
reasoning_effortenumno"medium"Reasoning depth: low, medium or high. Higher takes longer and uses more output tokens. high takes no max_tokens, temperature or top_p, and its response can be longer than 65,535 tokens. · Allowed: low, medium, high
reasoningstringno-Responses API reasoning object: {“effort”:“low|medium|high”}
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseReturn the answer without the Sources list that web search adds.

Notes

Reasoning traces are not returned. Video uploads up to ~1 GB.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/nova-lite-2.