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. GPT-6 Astra ProOpenAIRemove
  2. Mistral Medium 3.5MistralRemove
  3. Hy4 previewTencentRemove
gpt-6-astra-pro vs mistral-medium-3-5 vs hy4-preview
AttributeGPT-6 Astra Progpt-6-astra-proMistral Medium 3.5mistral-medium-3-5Hy4 previewhy4-preview
Pricing
Input$10.00 / 1M$1.50 / 1M$0.834 / 1M
Output$50.00 / 1M$7.50 / 1M$2.50 / 1M
Cache Write (5m)$10.00 / 1M$1.50 / 1M$0.834 / 1M
Cache Write (1h)$10.00 / 1M$1.50 / 1M$0.834 / 1M
Cache Read$10.00 / 1M$1.50 / 1M$0.834 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context1M262.1K1M
Max outputN/AN/AN/A
Capabilities
VisionYesYesYes
Function CallingYesYesYes
JSON ModeYesYesYes
StreamingYesYesYes
Catalogue
ProviderOpenAIMistralTencent
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released
Description
SummaryGPT-6 Astra Pro uses the same underlying model as GPT-6 Astra, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is well suited for demanding coding, analysis, and agentic workflows where solution quality takes priority over speed and cost.Mistral Medium 3.5 is a 128B dense instruction-following model from Mistral AI, supporting text and image inputs with text output. It is designed for agentic workflows, coding, and complex multi-step reasoning, with strong reliability in multi-tool orchestration and long-horizon tasks. The model features a 256K token context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. With support for self-hosting on as few as four GPUs and availability under open weights, it is well suited for scalable, production-grade deployments.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.