Nova Pro 1.0 with Jev
Nova Pro 1.0 is a model from Amazon, released 2024-12-05. It costs $0.800 per million input tokens and $3.20 per million output tokens, reads up to 300K tokens of context, and writes up to 5,120 tokens in one reply. Through llm11, set model to amazon/nova-pro-v1.
- Input price
- $0.800 / 1M
- Output price
- $3.20 / 1M
- Context window
- 300K tokens
- Max output
- 5K tokens
- Released
- 2024-12-05
- Accepts
- text, image
Read from the live catalogue and refreshed daily. At blended list price, 34% of the 332 priced models we can call cost more.
Using Nova Pro 1.0 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 Pro 1.0 does the answering when Jev sends it work, or when you name it yourself. At list price Nova Pro 1.0 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-pro-v1 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Nova Pro 1.0 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 | $0.00104 | $1.04 |
| Question over retrieved documents | 4,000 / 500 | $0.00480 | $4.80 |
| Long document summary | 30,000 / 1,000 | $0.027 | $27.20 |
Cheaper models to try
The catalogue has no benchmark score for Nova Pro 1.0, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3 Coder PlusRetires 2026-10-09 | $0.650 | $3.25 | 1M | |
| Qwen Qwen3 VL 235B A22B ThinkingRetires 2026-10-09 | $0.400 | $4.00 | 131K | |
| Qwen Qwen3.5 397B A17B | $0.550 | $3.50 | 262K | |
| SpaceXAI Grok Build 0.1 | $1.00 | $2.00 | 256K |
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-pro-v1",
messages=[{"role": "user", "content": "Hello"}],
)More from Amazon
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova 2 Lite | $0.300 | $2.50 | 1M | |
| 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 |
Questions
- What is Nova Pro 1.0 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 Pro 1.0 does the answering when Jev sends it work, or when you name it yourself. At list price Nova Pro 1.0 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-pro-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 Pro 1.0 a System One model?
- No. Nova Pro 1.0 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 Pro 1.0 cost?
- $0.800 per million input tokens and $3.20 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00480, so a thousand of them is about $4.80. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Nova Pro 1.0 context window?
- 300,000 tokens, with up to 5,120 tokens in a single reply.
- Does Nova Pro 1.0 support tool calling and structured output?
- The catalogue lists tool calling, but it does not list structured output and reasoning controls.
- Can I use Nova Pro 1.0 through llm11?
- Yes. Set model to amazon/nova-pro-v1 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Nova Pro 1.0?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Nova Pro 1.0 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-pro-v1 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Nova Pro 1.0?
- Nearest in price and below it: Qwen Qwen3 Coder Plus at $0.650 in and $3.25 out, Qwen Qwen3 VL 235B A22B Thinking at $0.400 in and $4.00 out and Qwen Qwen3.5 397B A17B at $0.550 in and $3.50 out. The catalogue has no benchmark score for Nova Pro 1.0, so this is a price ordering. It does not claim these answer as well.