Skip to content
Apertis
Get started

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. Llama 3.3 70B InstructMetaRemove
  2. Hy4 previewTencentRemove
  3. Qwen3.8 27BAlibabaRemove
llama-3.3-70b-instruct vs hy4-preview vs qwen3.8-27b
AttributeLlama 3.3 70B Instructllama-3.3-70b-instructHy4 previewhy4-previewQwen3.8 27Bqwen3.8-27b
Pricing
Input$0.10 / 1M$0.834 / 1M$0.45 / 1M
Output$0.25 / 1M$2.50 / 1M$3.20 / 1M
Cache Write (5m)$0.10 / 1M$0.834 / 1M$0.45 / 1M
Cache Write (1h)$0.10 / 1M$0.834 / 1M$0.45 / 1M
Cache Read$0.10 / 1M$0.834 / 1M$0.45 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context128K1M262K
Max outputN/AN/AN/A
Capabilities
VisionNoYesYes
Function CallingNoYesYes
JSON ModeNoYesYes
StreamingNoYesYes
Catalogue
ProviderMetaTencentAlibaba
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released———
Description
Summary—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.Qwen3.8 27B is an open-weight dense vision-language model from Qwen, designed for coding, professional knowledge work, research, and multimodal interaction. It combines strong text and visual understanding with capabilities optimized for sustained, real-world agentic tasks. The model supports flexible thinking modes that can be enabled for deeper reasoning or disabled for faster execution, making it well suited for long-running agents, multimodal workflows, coding assistants, and cost-conscious self-hosted deployments.