llm11

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.

About JevThe System One router

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.

RequestTokens in / outOneA thousand
Short chat turn500 / 200$0.00065$0.650
Question over retrieved documents4,000 / 500$0.00245$2.45
Long document summary30,000 / 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.

Cheaper alternatives to Nova 2 Lite
ModelInput / 1MOutput / 1MContext
Mistral Devstral 2 2512$0.400$2.00262K
Mistral Mistral Medium 3.1$0.400$2.00131K
Mistral Mistral Medium 3$0.400$2.00131K
Qwen Qwen3 235B A22BRetires 2026-10-09$0.455$1.82131K

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

Other Amazon models
ModelInput / 1MOutput / 1MContext
Nova Premier 1.0$2.50$131M
Nova Lite 1.0$0.060$0.240300K
Nova Micro 1.0$0.035$0.140128K
Nova Pro 1.0$0.800$3.20300K

All 5 Amazon models

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.