Nova 2 Lite with Jev
Nova 2 Lite is a model from Amazon, released 2025-12-02. It costs $0.300 per million input tokens and $2.50 per million output tokens, reads up to 1M tokens of context, and writes up to 65,535 tokens in one reply. Through llm11, set model to amazon/nova-2-lite-v1.
- Input price
- $0.300 / 1M
- Output price
- $2.50 / 1M
- Context window
- 1M tokens
- Max output
- 66K tokens
- Released
- 2025-12-02
- Accepts
- text, image, video, file
Read from the live catalogue and refreshed daily. At blended list price, 45% of the 332 priced models we can call cost more.
Using Nova 2 Lite with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Nova 2 Lite does the answering when Jev sends it work, or when you name it yourself. At list price Nova 2 Lite falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass amazon/nova-2-lite-v1 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Nova 2 Lite with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00065 | $0.650 |
| Question over retrieved documents | 4,000 / 500 | $0.00245 | $2.45 |
| Long document summary | 30,000 / 1,000 | $0.011 | $11.50 |
Cheaper models to try
The catalogue has no benchmark score for Nova 2 Lite, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Devstral 2 2512 | $0.400 | $2.00 | 262K | |
| Mistral Mistral Medium 3.1 | $0.400 | $2.00 | 131K | |
| Mistral Mistral Medium 3 | $0.400 | $2.00 | 131K | |
| Qwen Qwen3 235B A22BRetires 2026-10-09 | $0.455 | $1.82 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="amazon/nova-2-lite-v1",
messages=[{"role": "user", "content": "Hello"}],
)More from Amazon
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova Premier 1.0 | $2.50 | $13 | 1M | |
| Nova Lite 1.0 | $0.060 | $0.240 | 300K | |
| Nova Micro 1.0 | $0.035 | $0.140 | 128K | |
| Nova Pro 1.0 | $0.800 | $3.20 | 300K |
Questions
- What is Nova 2 Lite with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Nova 2 Lite does the answering when Jev sends it work, or when you name it yourself. At list price Nova 2 Lite falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass amazon/nova-2-lite-v1 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Nova 2 Lite a System One model?
- No. Nova 2 Lite answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Nova 2 Lite cost?
- $0.300 per million input tokens and $2.50 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00245, so a thousand of them is about $2.45. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Nova 2 Lite context window?
- 1,000,000 tokens, with up to 65,535 tokens in a single reply.
- Does Nova 2 Lite support tool calling and structured output?
- The catalogue lists tool calling and reasoning controls, but it does not list structured output.
- Can I use Nova 2 Lite through llm11?
- Yes. Set model to amazon/nova-2-lite-v1 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Nova 2 Lite?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Nova 2 Lite falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass amazon/nova-2-lite-v1 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Nova 2 Lite?
- Nearest in price and below it: Mistral Devstral 2 2512 at $0.400 in and $2.00 out, Mistral Mistral Medium 3.1 at $0.400 in and $2.00 out and Mistral Mistral Medium 3 at $0.400 in and $2.00 out. The catalogue has no benchmark score for Nova 2 Lite, so this is a price ordering. It does not claim these answer as well.