{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/deepseek-v3-2/","md":"https://postcutoff.com/m/deepseek-v3-2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"deepseek-v3-2","name":"DeepSeek-V3.2","org":"DeepSeek","family":"DeepSeek V3","released":"2025-12-01","status":"legacy","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"mit","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"DeepSeek API (retired)","model_id":"deepseek-chat / deepseek-reasoner (no longer serve V3.2)","endpoint":"https://api.deepseek.com","docs":"https://api-docs.deepseek.com/updates"},{"provider":"OpenRouter","model_id":"deepseek/deepseek-v3.2","url":"https://openrouter.ai/deepseek/deepseek-v3.2"},{"provider":"Hugging Face","url":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"provider":"Hugging Face (Speciale)","url":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale"}],"capabilities":[{"name":"DeepSeek Sparse Attention (DSA)","detail":"Introduced DSA (first in V3.2-Exp) to cut long-context attention compute while preserving quality.","first":false,"discovered":"launch","source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"name":"Hybrid thinking/non-thinking in one model","detail":"deepseek-chat mapped to non-thinking mode and deepseek-reasoner to thinking mode of the same V3.2 weights.","first":false,"discovered":"launch","source":"https://api-docs.deepseek.com/updates"},{"name":"V3.2-Speciale reasoning variant","detail":"Separate high-compute Speciale variant served briefly on a temporary endpoint (no tool calls) until 2025-12-15; weights released.","first":false,"discovered":"launch","source":"https://api-docs.deepseek.com/updates"}],"entry":null,"notes":"API aliases deepseek-chat/deepseek-reasoner moved to V4-Flash on 2026-04-24 and were scheduled for discontinuation on 2026-07-24; V3.2 now only via open weights/third parties. Pricing not verified (no first-party price).","verified":"2026-09-29","body_md":"Open-weight (MIT) predecessor of V4; still widely self-hosted and on third-party APIs. Use deepseek-v4-pro / deepseek-flash on the first-party API instead.\n\nSources: https://api-docs.deepseek.com/updates · https://huggingface.co/deepseek-ai/DeepSeek-V3.2 · https://openrouter.ai/deepseek/deepseek-v3.2","page_url":"https://postcutoff.com/m/deepseek-v3-2/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1968,"you_url":null,"briefings":null}