Question 1

What is Nova Lite 1.0?

Accepted Answer

Nova Lite 1.0 is a model from Bedrock, released on Dec 3, 2024. Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy. With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.

Question 2

How much does Nova Lite 1.0 cost?

Accepted Answer

On the Respan gateway, input starts at $0.06 per 1M tokens on OpenRouter, and output starts at $0.24 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Nova Lite 1.0 on Respan?

Accepted Answer

Nova Lite 1.0 is served by OpenRouter.

Question 4

What is Nova Lite 1.0's context window?

Accepted Answer

Nova Lite 1.0 accepts up to 300K tokens of context.

Question 5

How do I use Nova Lite 1.0 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "nova-lite-v1". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Nova Lite 1.0?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 88 tokens per second, and the lowest response latency was 0.6 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Nova Lite 1.0 score on benchmarks?

Accepted Answer

Nova Lite 1.0 has 8 published benchmark scores, including ARC-C 92.4%, GSM8K 94.5%, and IFEval 89.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Nova Lite 1.0

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Certified where it counts.

Benchmarks

Reasoning4

Math2

Knowledge2

Apps

Nova Lite 1.0 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.