Skip to main content

Nova 2 Lite

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.

Input / output price
$0.30 / $2.50 per 1M
Context
1M tokens
Released
Dec 2, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "bedrock/global.amazon.nova-2-lite-v1:0".

Read docs

Providers

5 routes from 4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Bedrockbedrock/global.amazon.nova-2-lite-v1:0
$0.30/M$2.50/M
Concentrateconcentrate/nova-2-lite
$0.30/M$2.50/M
Bedrockbedrock/us.amazon.nova-2-lite-v1:0
$0.33/M$2.75/M
EmpirioLabsempiriolabs/nova-lite-2
$0.38/M$3.16/M
OpenRouteropenrouter/nova-2-lite-v1
$0.30/M$2.50/M

Is a provider down? AWS Bedrock status, OpenRouter status

Pricing

Averaged across 5 routes from 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.32 per 1M
Average output
$2.68 per 1M
Average cache read
$0.12 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.38/MEmpirioLabsLowest$0.30/MBedrock, Concentrate, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

11tokens/sacross providers

Faster than 21% of the other 599 models on the gateway

Response latency

Lower is better

0.5sacross providers

Faster than 85% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 13 published scores from 2 sources, each linked to where it was published.

15.8/ 100

Respan Index#157 of 176

176 ranked models. The shaded band is this model's 95% interval, 11.6 to 26.6. GPT-4o and NVIDIA Nemotron 3 Nano 30B-A3B BF16 fall inside it, so the gap is within the margin of error.
Nova 2 Lite by category: Coding 3.5 (estimated), Agents 8.5, Reasoning 23.8, Knowledge & language 13.0, Human preference 36.9
  1. 157Amazon Nova 2 Lite15.8
  2. 156GPT-4o15.9
  3. 158NVIDIA Nemotron 3 Nano 30B-A3B BF1615.6

Published scores

BenchmarkScore
LongCodeBench 1Mcdn.amazon.science84%

Apps

Use Nova 2 Lite in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Nova 2 Lite FAQ

Short answers, built from the data on this page.

Nova 2 Lite is a model from Bedrock, released on Dec 2, 2025. Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.

On the Respan gateway, Nova 2 Lite costs from $0.30 per 1M input tokens and $2.50 per 1M output tokens on Bedrock, Concentrate, and OpenRouter, after gateway discounts. Averaged across its 5 routes from 4 providers, it costs $0.32 per 1M input tokens and $2.68 per 1M output tokens.

Nova 2 Lite is available through 5 routes from 4 providers: Bedrock, Concentrate, EmpirioLabs, and OpenRouter.

Nova 2 Lite accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "bedrock/global.amazon.nova-2-lite-v1:0". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Nova 2 Lite scores 15.8 out of 100 on the Respan Index v1.1, ranking #157 of 176 models. By category: Coding 3.5 (estimated), Agents 8.5, Reasoning 23.8, Knowledge & language 13.0, and Human preference 36.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Nova 2 Lite has 13 published benchmark scores, including LongCodeBench 1M 84%, tau2-bench Retail Verified 76.5%, and GPQA Diamond 79.6%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.