Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Nemotron 3.5 LightningNVIDIARemove
  2. Gemini 3.1 Flash Lite Image (Google AI Studio)GoogleEnterprise & partner accessRemove
  3. Perceptron Mk1.5PerceptronRemove
nemotron-3.5-lightning vs gemini-3.1-flash-lite-image-aistudio vs perceptron-mk1.5
AttributeNemotron 3.5 Lightningnemotron-3.5-lightningGemini 3.1 Flash Lite Image (Google AI Studio)gemini-3.1-flash-lite-image-aistudioPerceptron Mk1.5perceptron-mk1.5
Pricing
Input— Not priced per input token—$0.15 / 1M
Output— Not priced per output token—$1.50 / 1M
Cache Write (5m)$0.00 / 1MNot applicable$0.15 / 1M
Cache Write (1h)$0.00 / 1MNot applicable$0.15 / 1M
Cache Read$0.00 / 1MNot applicable$0.15 / 1M
Web Search$0 / 1M—$0 / 1M
Request—$0.0336 / request—
Billing—Pay Per Request—
Context
Max context1MN/A36.9K
Max outputN/AN/AN/A
Capabilities
VisionYesYesNo
Function CallingYesNoNo
JSON ModeYesNoNo
StreamingYesNoYes
Catalogue
ProviderNVIDIAGooglePerceptron
Categorychatimagechat
Charge typePay As You GoPay Per RequestPay As You Go
Released——2026-09-25
Description
SummaryNVIDIA Nemotron 3.5 Lightning is an open Mixture-of-Experts (MoE) model with 30B total parameters and 3B active per token, optimized for high-throughput agentic workloads and efficient inference. Its lightweight active compute and open design make it well suited for specialized agents, domain-specific customization, and scalable production deployments where speed, cost efficiency, and adaptability are key.Gemini 3.1 Flash Lite Image served from Google AI Studio. Billed per image at US$0.0336. Call it through /v1/chat/completions with stream set to false; the image is returned in the message content as a base64 data URI. Maximum output resolution is 1K. A request for a larger size returns a 1K image with the same aspect ratio at the same price. When a size is reduced, the response carries an X-Image-Resolution-Capped header with the requested and delivered size.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.