DeepSeek V3.2

deepseek/deepseek-v3.2

Maker: DeepSeek, China
Released: 2025-12-01
Knowledge cutoff: 2024-07
Family: deepseek
Weights: open
Tasks: text.chat, text.reasoning, code
Cheapest offering: DeepInfra, about $0.000374 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Azure OpenAI	`deepseek-v3.2`	ga	Input: $0.58 Output: $1.68 Since 2026-11-04 · models.dev, MIT	none	Context: 128,000 tokens Max output: 128,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `reasoning` claimed
Amazon Bedrock	`deepseek.v3.2`	ga	Input: $0.62 Output: $1.85 Since 2026-11-03 · models.dev, MIT	none	Context: 163,840 tokens Max output: 81,920 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Alibaba Cloud Model Studio (DashScope)	`siliconflow/deepseek-v3.2`	ga	Input: $0.27 Output: $0.42 Since 2026-11-04 · models.dev, MIT	none	Context: 163,840 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
DeepInfra	`deepseek-ai/DeepSeek-V3.2`	ga	Input: $0.26 Output: $0.38 Cache read: $0.13 Since 2026-11-03 · models.dev, MIT	none	Context: 163,840 tokens Max output: 64,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`deepseek/deepseek-v3.2`	ga	Input: $0.26 Output: $0.38 Cache read: $0.13 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 163,840 tokens Max output: 147,456 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:terminal_bench`	0.467	0.3955	2025-12-01	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`lmarena:webdev`	0.116	1325.7507	2026-10-28	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

deepseek-ai/deepseek-v3.2
deepseek.v3.2

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/deepseek/deepseek-v3.2' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=azure-openai,bedrock,dashscope,deepinfra,openrouter' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).