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. Gemini 3.1 Flash Lite Image (Google Vertex AI)GoogleRemove
  2. Nemotron 3.5 LightningNVIDIARemove
  3. Perceptron Mk1.5PerceptronRemove
gemini-3.1-flash-lite-image-vertex vs nemotron-3.5-lightning vs perceptron-mk1.5
AttributeGemini 3.1 Flash Lite Image (Google Vertex AI)gemini-3.1-flash-lite-image-vertexNemotron 3.5 Lightningnemotron-3.5-lightningPerceptron Mk1.5perceptron-mk1.5
Pricing
Request$0.0336 / request——
BillingPay Per Request——
Cache Write (5m)Not applicable$0.00 / 1M$0.15 / 1M
Cache Write (1h)Not applicable$0.00 / 1M$0.15 / 1M
Cache ReadNot applicable$0.00 / 1M$0.15 / 1M
Input—— Not priced per input token$0.15 / 1M
Output—— Not priced per output token$1.50 / 1M
Web Search—$0 / 1M$0 / 1M
Context
Max contextN/A1M36.9K
Max outputN/AN/AN/A
Capabilities
VisionYesYesNo
Function CallingNoYesNo
JSON ModeNoYesNo
StreamingNoYesYes
Catalogue
ProviderGoogleNVIDIAPerceptron
Categoryimagechatchat
Charge typePay Per RequestPay As You GoPay As You Go
Released——2026-09-25
Description
SummaryGemini 3.1 Flash Lite Image served from Google Vertex AI. 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.NVIDIA 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.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.