DeepSeek V3.2

deepseek-v3.2

A hybrid-reasoning model with thinking and non-thinking modes, sparse attention, and tool use.

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

128K context128K context

Released2025-12-01

Relays9 sites

reasoninglong contexttool use

Model information

Model ID: deepseek-v3.2
Context: 128K
Max input: -
Max output: 64K
Knowledge cutoff: 2024-07
Open weights: Supported
License: MIT License
Release date: 2025-12-01

Input

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit

OmniaKey

omniakey.comToken billing

Price range ¥0.52 / 1M tokens

Cache hit¥0.05

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥0.52	¥0.78	¥0.05	-

ClaudeCN

claudecn.topToken billing

Price range ¥1.8 / 1M tokens

Cache hit¥0.1929

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型	Token	¥1.8	¥2.7	¥0.1929	-

RunAPI

https://runapi.hostToken billing

Price range ¥1.22 - ¥1.54 / 1M tokens

Cache hit¥0.3086

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥1.22	¥1.82	-	-
default	Token	¥1.54	¥2.31	¥0.3086	-

AIGC Token

aigc-token.comToken billing

Price range ¥2 - ¥8 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
AzurePlus	Token	¥2	¥3	¥0.4	-
default	Token	¥2	¥3	¥0.4	-
AzurePro	Token	¥8	¥12	¥1.6	-

niccom

niccom.com.cnToken billing

Price range ¥0.38 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥0.38	¥0.6	-	-

猫云API

api.nekocloud.vipToken billing

Price range ¥2 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
deepinfra	Token	¥2	¥3	¥1.5	¥0

A6api

a6api.comToken billing

Price range ¥0.6407 / 1M tokens

Cache hit¥0.0641

Channel	Billing	Input	Output	Cache hit	Cache write
marketplace	Token	¥0.6407	¥0.9611	¥0.0641	-

镜核 AI

ai.17nas.comToken billing

Price range ¥0.38 - ¥0.5 / 1M tokens

Cache hit¥0.0076

Cache hit¥0.01

Channel	Billing	Input	Output	Cache hit	Cache write
cn	Token	¥0.38	¥0.76	¥0.0076	-
default	Token	¥0.5	¥1	¥0.01	-

ePhone AI

ephone.aiToken billing

Price range ¥1.06 - ¥1.6 / 1M tokens

deepseek-official-cheap

Channel	Billing	Input	Output	Cache hit	Cache write
deepseek-official-cheap	Token	¥1.06	¥1.59	-	-
deepseek	Token	¥1.6	¥2.4	-	-

How should DeepSeek V3.2 relay pricing be compared?

This DeepSeek V3.2 pricing page compares official pricing with public prices from 9 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 10/23/2026, 08:15.

Data sources: Public price catalogs, official pricing records, and monitoring results.
Metric definitions: Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note: Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.