Type
Spec
Rate
Input
per 1M prompt tokens
$0.38
Output
per 1M generated tokens
$3.16
Cached input
per 1M tokens
$0.2128
Web Search (Linkup)
per call when invoked
$0.013
Nova Lite 2 and Nova Lite 1.0 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Amazon Text GenerationNova Lite 2 and Nova Lite 1.0 are both Amazon models in the Text Generation category, available through the EmpirioLabs API.
| Spec | Nova Lite 2 | Nova Lite 1.0 |
|---|---|---|
| Model ID | nova-lite-2 | nova-lite-1-0 |
| Author | Amazon | Amazon |
| Released | Dec 2, 2025 | Dec 3, 2024 |
| Context window | 1M tokens | 317.4K tokens |
| Max output | 131,072 tokens | 10,000 tokens |
| Input | Text Image Video Document | Text Image Video |
| Output | Text | Text |
| Structured output | Not supported | Not supported |
| Batch API | Available, 35% off list price | Available, 35% off list price |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/nova-lite-2:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/nova-lite-1-0:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Nova Lite 2 | Nova Lite 1.0 |
|---|---|---|
| temperature | 0 to 1 Default: 0.7 | 0 to 1 Default: 0.7 |
| top_p | 0 to 1 Default: 0.9 | 0 to 1 Default: 0.9 |
| max_tokens | 1 to 65535 Default: 60000 | 1 to 10000 Default: 10000 |
| stop | string | string |
| enable_thinking | boolean Default: true | - |
| reasoning_effort | low, medium, high Default: medium | - |
| reasoning | string | - |
| web_search_linkup | boolean Default: false | boolean Default: false |
| disable_formatting | boolean Default: false | boolean Default: false |
Reasoning traces are not returned. Video uploads up to ~1 GB.
Nova Lite 2 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id nova-lite-2. Both models are called through the same endpoint. Set model to nova-lite-2 or nova-lite-1-0. Get an API key from the EmpirioLabs dashboard.
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": "Write a haiku about the ocean."}
]
}'Nova Lite 2 is the newer release (Dec 2, 2025); Nova Lite 1.0 was released on Dec 3, 2024. Nova Lite 2 has the larger context window: 1M tokens, against 317.4K for Nova Lite 1.0. Nova Lite 2 returns up to 131,072 output tokens per response, Nova Lite 1.0 up to 10,000. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Nova Lite 2 is the newer release (Dec 2, 2025); Nova Lite 1.0 was released on Dec 3, 2024.
Nova Lite 1.0 lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.