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. Hy4 previewTencentRemove
  3. Gemini 4 ArgonGoogleRemove
gemini-3.1-flash-lite-image-vertex vs hy4-preview vs gemini-4-argon
AttributeGemini 3.1 Flash Lite Image (Google Vertex AI)gemini-3.1-flash-lite-image-vertexHy4 previewhy4-previewGemini 4 Argongemini-4-argon
Pricing
Request$0.0336 / request——
BillingPay Per Request——
Cache Write (5m)Not applicable$0.834 / 1M$2.00 / 1M
Cache Write (1h)Not applicable$0.834 / 1M$2.00 / 1M
Cache ReadNot applicable$0.834 / 1M$2.00 / 1M
Input—$0.834 / 1M$2.00 / 1M
Output—$2.50 / 1M$10.00 / 1M
Web Search—$0 / 1M$0 / 1M
Context
Max contextN/A1M1M
Max outputN/AN/AN/A
Capabilities
VisionYesYesYes
Function CallingNoYesYes
JSON ModeNoYesYes
StreamingNoYesYes
Catalogue
ProviderGoogleTencentGoogle
Categoryimagechatchat
Charge typePay Per RequestPay As You GoPay As You Go
Released———
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.Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world workflows.Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.