DeepSeek V3.2 Exp
DeepSeek's V3.2 Exp joins the catalog through BYOK: an experimental open-weight model that adds DeepSeek Sparse Attention for long-context efficiency.
deepseek/deepseek-v3.2-exp is DeepSeek's experimental model built on V3.1-Terminus. It adds DeepSeek Sparse Attention to improve long-context training and inference efficiency, and DeepSeek reports benchmark results on par with V3.1-Terminus. It takes text, answers in text, and its weights are released under the MIT license.
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({
model: anyrouter("deepseek/deepseek-v3.2-exp"),
prompt: "Summarize the key obligations in this contract excerpt.",
})
console.log(text)curl -fsSL https://anyrouter.dev/setup.sh | bash
anyr login
anyr claude --model "deepseek/deepseek-v3.2-exp"DeepSeek V3.2 Exp is BYOK-only. Add a Computrix key under Dashboard → BYOK; AnyRouter charges nothing for a BYOK route and Computrix bills you at its own rate.
Playbooks: AI SDK, OpenAI SDK, coding agents, playground.
Looking for the full catalog?Muốn xem toàn bộ danh mục?想看完整目录? Browse all modelsXem tất cả model浏览全部模型.