← all models

DeepSeek V3.2

deepseek

openrouter
Parameters — not published
Context 160K 163840 tokens
Input $0.26 OpenRouter
Output $0.38 OpenRouter
Cache read $0.13 OpenRouter

Accepts

text

Capabilities

frequency_penalty include_reasoning logit_bias logprobs max_tokens min_p presence_penalty reasoning repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_k top_logprobs top_p

Description

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter deepseek/deepseek-v3.2 huggingface deepseek-ai/DeepSeek-V3.2 version slug deepseek/deepseek-v3.2-20251201 name DeepSeek: DeepSeek V3.2 display name DeepSeek V3.2

Identifiers

Vendor
deepseek
OpenRouter
deepseek/deepseek-v3.2
Hugging Face
deepseek-ai/DeepSeek-V3.2
Version slug
deepseek/deepseek-v3.2-20251201
Released
2025-12-01T13:10:42.000Z
First seen
59 d ago
Last crawled
16 min ago