Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
  1. Home
  2. /
  3. Compare

Nemotron 3.5 Lightning vs Extract

Compare Nemotron 3.5 Lightning from Nvidia and Extract from Scaledown on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for nvidia
Nemotron 3.5 Lightning
Favicon for scaledown
Extract
Favicon for nvidia
Nemotron 3.5 Lightning
Favicon for scaledown
Extract

Overview

Nemotron 3.5 Lightning
Author
Nvidia
Extract
Author
Scaledown
Nemotron 3.5 Lightning
Context length
262Ktokens
Extract
Context length
1Mtokens
Nemotron 3.5 Lightning
Reasoning
Extract
Reasoning
Nemotron 3.5 Lightning
Input modalities
Extract
Input modalities
Nemotron 3.5 Lightning
Output modalities
Extract
Output modalities

Nemotron 3.5 Lightning vs Extract: side-by-side summary

Nemotron 3.5 Lightning and Extract are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Nemotron 3.5 Lightning, from Nvidia, has a 262,144-token context window and is priced at $0.025/M tokens input, $0.12/M tokens output on OpenRouter.

Extract, from Scaledown, has a 1,000,000-token context window and is priced at $0.04/M tokens input, $0/M tokens output on OpenRouter.

Context window
  • Nemotron 3.5 Lightning: 262,144 tokens
  • Extract: 1,000,000 tokens
Price
  • Nemotron 3.5 Lightning: $0.025/M tokens input, $0.12/M tokens output
  • Extract: $0.04/M tokens input, $0/M tokens output
Provided by
  • Nemotron 3.5 Lightning: Nvidia
  • Extract: Scaledown
  • Nemotron 3.5 Lightning model details, providers and pricing
  • Extract model details, providers and pricing

Nemotron 3.5 Lightning vs Extract at a glance

Nemotron 3.5 Lightning vs Extract comparison
AttributeNemotron 3.5 LightningExtract
Input price$0.025/M tokens$0.04/M tokens
Output price$0.12/M tokens$0/M tokens
Context window262,144 tokens1,000,000 tokens
Intelligence Index12.9Not available
Coding Index26.8Not available
Agentic Index3.5Not available
Latency (p50)1.28 s0.98 s
Throughput (p50)73.0 tok/s783.0 tok/s

Benchmark data updated Oct 13, 2026

Frequently asked questions

Is Nemotron 3.5 Lightning cheaper than Extract?

Nemotron 3.5 Lightning and Extract trade off on price: Nemotron 3.5 Lightning costs $0.025/M tokens input and $0.12/M tokens output, while Extract costs $0.04/M tokens input and $0/M tokens output, so Nemotron 3.5 Lightning is cheaper for input tokens and Extract is cheaper for output tokens.

Which has the longer context window, Nemotron 3.5 Lightning or Extract?

Extract has the longer context window at 1,000,000 tokens, compared with 262,144 tokens for Nemotron 3.5 Lightning.

Which is faster, Nemotron 3.5 Lightning or Extract?

Extract is faster on OpenRouter, generating a median 783.0 tokens per second compared with 73.0 tokens per second for Nemotron 3.5 Lightning.