Nova Lite 1.0 pricing and routing profile
Nova Lite 1.0 from Amazon lists at $0.06 per million input tokens and $0.24 per million output tokens, with a 300,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool calling
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.0384 |
| Chat reply (2,000 in, 400 out) | $0.216 |
| Retrieval-augmented answer (8,000 in, 500 out) | $0.60 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for Nova Lite 1.0. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Who serves Nova Lite 1.0
| Host | Input / output per 1M | Log probabilities | Uptime, last 30 min |
|---|---|---|---|
| Amazon Bedrock | $0.06 / $0.24 | no | 100.0% |
| Amazon Bedrock | $0.06 / $0.24 | no | 100.0% |
A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.
Cheaper models that can answer first
Models priced below Nova Lite 1.0 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Nemotron 3 Nano 30B A3B | $0.05 / $0.20 | 17% |
| Llama 3.1 8B Instruct | $0.05 / $0.08 | 39% |
| Qwen3.7 Flash | $0.03 / $0.13 | 48% |
| Granite 4.0 Micro | $0.017 / $0.112 | 64% |
| gpt-oss-20b | $0.018 / $0.09 | 67% |
| Ling 3.0 Flash | $0.021 / $0.063 | 69% |
Compare Nova Lite 1.0
- Nova Lite 1.0 vs Claude Opus 5.5
- Nova Lite 1.0 vs Claude Sonnet 5
- Nova Lite 1.0 vs Claude Fable 5.1
- Nova Lite 1.0 vs Claude Opus 5
- Nova Lite 1.0 vs GPT-6 Sol
- Nova Lite 1.0 vs GPT-6 Astra
- Nova Lite 1.0 vs GPT-5.6 Sol
- Nova Lite 1.0 vs GPT-5.6 Terra
- Nova Lite 1.0 vs GPT-5.5
- Nova Lite 1.0 vs GPT-5.4
- Nova Lite 1.0 vs Gemini 3.1 Pro Preview
- Nova Lite 1.0 vs Gemini 3.8 Flash
- Nova Lite 1.0 vs Grok 4.7
- Nova Lite 1.0 vs Qwen3.8 Max (0902)
- Nova Lite 1.0 vs Kimi K3
- Nova Lite 1.0 vs GLM 5.3
- Nova Lite 1.0 vs DeepSeek V4 Pro 0423
- Nova Lite 1.0 vs Mistral Large 3 2512
- Nova Lite 1.0 vs Nova Premier 1.0
- Nova Lite 1.0 vs Command A
- Nova Lite 1.0 vs GPT-6 Luna
- Nova Lite 1.0 vs GPT-5.6 Luna
- Nova Lite 1.0 vs GPT-5.4 Mini
- Nova Lite 1.0 vs GPT-5.4 Nano
- Nova Lite 1.0 vs GPT-4.1 Mini
- Nova Lite 1.0 vs gpt-oss-120b
- Nova Lite 1.0 vs gpt-oss-20b
- Nova Lite 1.0 vs Claude Haiku 4.5
- Nova Lite 1.0 vs Gemini 3.5 Flash Lite
- Nova Lite 1.0 vs Gemma 4 31B
- Nova Lite 1.0 vs DeepSeek V4.1 Flash
- Nova Lite 1.0 vs DeepSeek V4 Flash 0731
- Nova Lite 1.0 vs GLM 5.3 Flash
- Nova Lite 1.0 vs Hy4 preview
- Nova Lite 1.0 vs MiMo-V2.6-Flash
- Nova Lite 1.0 vs Nemotron 3.5 Lightning
- Nova Lite 1.0 vs Nemotron 3 Ultra
- Nova Lite 1.0 vs Qwen3.8 Flash
- Nova Lite 1.0 vs Qwen3.7 Flash
- Nova Lite 1.0 vs Qwen3.8 27B
- Nova Lite 1.0 vs MiniMax M3
- Nova Lite 1.0 vs Kimi K2.6
- Nova Lite 1.0 vs Mistral Small 4
- Nova Lite 1.0 vs Ministral 3 8B 2512
- Nova Lite 1.0 vs Llama 4 Maverick
- Nova Lite 1.0 vs Llama 3.3 70B Instruct
- Nova Lite 1.0 vs Nova Micro 1.0
- Nova Lite 1.0 vs Command R7B (12-2024)
- Nova Lite 1.0 vs Phi 4
Questions
How much does Nova Lite 1.0 cost?
Nova Lite 1.0 lists at $0.06 per million input tokens and $0.24 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.216 per 1,000 requests.
What is the context window of Nova Lite 1.0?
300,000 tokens.
Can a cheaper model replace Nova Lite 1.0?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Nova Lite 1.0 on one half of your requests and make at most three answers worse on the other.