DeepSeek V4 Pro 0813

deepseek-v4-pro-0813

A model snapshot with million-token context and both thinking and non-thinking modes.

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

1M context1M context

Released2026-08-12

Relays29 sites

reasoninglong contexttool use

Model information

Model ID: deepseek-v4-pro-0813
Context: 1M
Max input: -
Max output: 384K
Knowledge cutoff: -
Open weights: Supported
License: MIT
Release date: 2026-08-12

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

DeepSeek Official Pricing

CNY

Updated: 2026-10-04T22:55:10.536+08:00

Input

~¥4.415/ 1M tokens

Output

~¥13.245/ 1M tokens

Cache read

~¥0.1472/ 1M tokens

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

MX-AI

mxzzz.xyzToken billing

Price range ¥0.675 - ¥1.35 / 1M tokens

国模全家桶-openai接口

Cache hit¥0.09

国模高缓存-openai接口

Cache hit¥0.18

Channel	Billing	Input	Output	Cache hit	Cache write
国模全家桶-openai接口	Token	¥0.675	¥4.05	¥0.09	-
国模高缓存-openai接口	Token	¥1.35	¥8.1	¥0.18	-

T8 API

t8api.comToken billing

Price range ¥2.25 / 1M tokens

国产模型聚合

Cache hit¥0.075

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型聚合	Token	¥2.25	¥6.75	¥0.075	-

OmniaKey

omniakey.comToken billing

Price range ¥1.01 / 1M tokens

Cache hit¥0.099

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥1.01	¥3.02	¥0.099	-

AutoRouter

autorouter.netToken billing

Price range ¥45 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型	Token	¥45	¥45	-	-

Token-AI

tken.lolToken billing

Price range ¥1.35 - ¥2.25 / 1M tokens

Cache hit¥0.09

国模高缓分组

Cache hit¥0.15

Channel	Billing	Input	Output	Cache hit	Cache write
国模分组	Token	¥1.35	¥4.05	¥0.09	-
国模高缓分组	Token	¥2.25	¥6.75	¥0.15	-

LinoRoute

linoroute.comToken billing

Price range ¥0.792 - ¥1.98 / 1M tokens

Self-Deployed-1

Cache hit¥0.0264

Self-Deployed-2

Cache hit¥0.044

Self-Deployed-3

Cache hit¥0.066

Channel	Billing	Input	Output	Cache hit	Cache write
Self-Deployed-1	Token	¥0.792	¥2.38	¥0.0264	-
Self-Deployed-2	Token	¥1.32	¥3.96	¥0.044	-
Self-Deployed-3	Token	¥1.98	¥5.94	¥0.066	-

niccom

niccom.com.cnToken billing

Price range -

deepseek专属特价

Channel	Billing	Input	Output	Cache hit	Cache write
deepseek专属特价	Token	-	-	-	-

ITKK

itkk.lolToken billing

Price range -

China-Ai-福利

Channel	Billing	Input	Output	Cache hit	Cache write
China-Ai-福利	Token	-	-	-	-

Moniker

aimoniker.topToken billing

Price range ¥5.4 / 1M tokens

Cache hit¥0.18

Channel	Billing	Input	Output	Cache hit	Cache write
DeepSeek	Token	¥5.4	¥16.2	¥0.18	-

Moe Api

moeapi.cloudToken billing

Price range ¥2.7 / 1M tokens

Cache hit¥0.09

Channel	Billing	Input	Output	Cache hit	Cache write
DeepSeek	Token	¥2.7	¥8.1	¥0.09	-

How should DeepSeek V4 Pro 0813 relay pricing be compared?

This DeepSeek V4 Pro 0813 pricing page compares official pricing with public prices from 29 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, 08:16.

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.