Nova Lite 2
nova-lite-2Pricing
List prices at EmpirioLabs AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.38 | $3.16 | |
| Cached input 44% off input | $0.213 | 44% off input |
What it costs a month
At EmpirioLabs AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$336
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$256
- Coding agent1,000 requests a day, 40K in / 2K out, cached$505
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,670
Where to run it
1 host serve Nova Lite 2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud nova-lite-2 | $0.38 / $3.16 | nova-lite-2 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than EmpirioLabs AI.
Smaller Amazon models
- 21% less
- 90% less
- 94% less
Other frontier labs
- 21% less
- 57% less
- 81% less
- 81% less
Open-weight picks
- 36% less
- 41% less
- 51% less
- 55% less
Model line
Newer and older versions, at each lab's own price.
- UndatedNova 2 LiteLatest$0.30 / $2.50
- UndatedNova Lite 2This page$0.38 / $3.16
- UndatedNova Lite 1.0$0.069 / $0.28
Call it
Using EmpirioLabs AI's API.
from litellm import completion
response = completion(
model="empiriolabs/nova-lite-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Nova Lite 2 cost?
On EmpirioLabs AI, Nova Lite 2 costs $0.38 per million input tokens and $3.16 per million output tokens. Cached input costs $0.213 per million tokens.
Which APIs offer Nova Lite 2?
Nova Lite 2 runs on 1 API: EmpirioLabs AI.
What is Nova Lite 2's context window?
1M tokens, with up to 131K tokens in one reply.
Is Nova Lite 2 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Nova Lite 2?
Yes. Nova 2 Lite is the newest model in this line.
What are cheaper alternatives to Nova Lite 2?
Models that cost less and keep most of what it can do: Nova 2 Lite on Amazon Bedrock (21% less), Gemini 3.5 Flash Lite on Google AI Studio (21% less), GPT-5.4 Nano on OpenAI (57% less) and Kimi K2.7 Code on CLF AI Gateway (36% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Nova Lite 2's API model id?
Use nova-lite-2 with EmpirioLabs AI.
Sources
Raw catalog entry for nova-lite-2 on EmpirioLabs AI
{
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"input_cost_per_token": 3.8e-7,
"output_cost_per_token": 0.00000316,
"cache_read_input_token_cost": 2.128e-7,
"supports_system_messages": true,
"supports_vision": true,
"supports_reasoning": true,
"supports_prompt_caching": true,
"source": "https://empiriolabs.ai/models/nova-lite-2",
"supports_function_calling": true
}