探索 OpenCode 中使用的 2 個 Tencent 模型 包括 Hy3和Hy3 preview. 比較近期 token 用量、上下文視窗、發布日期和模型專屬數據。
#用量. 過去兩個月的每日 OpenCode token 用量。
#模型. 近期使用量和限制。
#Related labs. Explore more.
DeepSeek is an open-model lab known for cost-efficient reasoning systems, visible reasoning APIs, and strong coding and math performance.
DeepSeek V4 Flash + 4 other models
MiniMax builds agentic models for coding, office work, and multimodal media, with a strong bias toward practical productivity workflows.
MiniMax-M3 + 6 other models
Xiaomi's MiMo models target coding agents and real-world automation with long-context reasoning, multimodal interaction, and compatible APIs.
MiMo-V2.5-Pro-UltraSpeed + 5 other models
Tencent Model Comparisons. Model pairs from this lab.