Choosing Models

Context works with whichever model your Agent runs, but the choice changes speed and cost a lot. The roles below come from teams' experience; the model names are examples of each role at the time of writing, not endorsements.

Four roles

Role	Example	Use it for
Primary	Claude Opus 5.5	First creation, everyday production and querying. Roughly two to three times faster than the others, and in practice it consumes less.
Balanced	GPT 5.6 SOL, Grok 4.6	Moderate speed and cost; text, code and medium-intensity code exploration.
Low-cost and fast	DeepSeek 4.1 Flash	Processing documents meant for people and summarizing code.
High-end	GPT 6.0 Astra	Planning the first build of a very large knowledge base and deep attribution in code. Expensive.

For large work you do not need to orchestrate several Agents yourself: Context's built-in multi-Agent scheduling runs the work in parallel.

How much it matters when answering

In one benchmark run, with the same knowledge and the same retrieval method, two models both fully resolved 23 of 24 questions — but one averaged 139.3 seconds and the other 304.0 seconds, about 2.2 times as long. At equal quality, model choice can more than double answer time.

This is a single run on one question set, so treat it as an indication rather than a ranking. The method and its limits are in Knowledge Retrieval Benchmark; to measure your own setup, see Evaluating Your Knowledge Base.

模型选择

Context 可以搭配你的 Agent 所运行的任意模型，但模型选择会显著影响速度和成本。下面的角色划分来自各团队的经验；模型名称只是撰写时各角色的示例，并非推荐背书。

四种角色

角色	示例	适用场景
主力	Claude Opus 5.5	首次创建、日常生产和查询。速度约为其他模型的两到三倍，实际消耗也更少。
均衡	GPT 5.6 SOL, Grok 4.6	速度和成本适中；适合文本、代码以及中等强度的代码探索。
低成本、快速	DeepSeek 4.1 Flash	处理面向人阅读的文档、总结代码。
高端	GPT 6.0 Astra	规划超大知识库的首次构建，以及在代码中做深度归因。价格昂贵。

处理大型工作时，你不需要自己编排多个 Agent：Context 内置的多 Agent 调度会并行执行这些工作。

对回答的影响有多大

在一次测评中，使用相同的知识和相同的检索方式，两个模型都完全解决了 24 道题中的 23 道，但一个平均耗时 139.3 秒，另一个平均 304.0 秒，约为前者的 2.2 倍。在质量相同的情况下，模型选择可能让回答耗时翻倍以上。

这只是在一套题集上的单次运行，请把它当作参考，而不是排名。方法及其局限见知识检索测评；如果要测量你自己的配置，参见评测知识库效果。