DeepSeek

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
Relays28 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

~¥4.412/ 1M tokens

Output

~¥13.236/ 1M tokens

Cache read

~¥0.1471/ 1M tokens

Relay Comparison

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

How should DeepSeek V4 Pro 0813 relay pricing be compared?

This DeepSeek V4 Pro 0813 pricing page compares official pricing with public prices from 28 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: 10/25/2026, 23:15.

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.