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 2.5 Flash Image PreviewGoogleRemove
  2. Hy4 previewTencentRemove
gemini-2.5-flash-image-preview vs hy4-preview
AttributeGemini 2.5 Flash Image Previewgemini-2.5-flash-image-previewHy4 previewhy4-preview
Pricing
Request$0.075 / request
BillingPay Per Request
Cache Write (5m)Not applicable$0.834 / 1M
Cache Write (1h)Not applicable$0.834 / 1M
Cache ReadNot applicable$0.834 / 1M
Input$0.834 / 1M
Output$2.50 / 1M
Web Search$0 / 1M
Context
Max contextN/A1M
Max outputN/AN/A
Capabilities
VisionNoYes
Function CallingNoYes
JSON ModeNoYes
StreamingYesYes
Catalogue
ProviderGoogleTencent
Categoryimagechat
Charge typePay Per RequestPay As You Go
Released
Description
SummaryGemini 2.5 Flash Image Preview (“Nano Banana”) is a cutting-edge image generation model with strong contextual understanding. It can create and edit images and supports multi-turn conversational workflows around visuals.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.