Skip to main content
Chinese AI Tools
ProductsModelsIntegrationsRankingsLatest changes
TopicsAvailability TrackerUse casesSubmit a toolAccount
ZHSearch

Chinese AI Tools

Independent directory for Chinese AI products. Product availability, pricing and terms can change. Verify before commercial use.

Editorial standardsClaim productUpdate infoGet featuredAdvertise
All models

DeepSeek · DeepSeek V4

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

The hosted V4 Pro snapshot currently served by DeepSeek's official API, with million-token context, 384K output and peak/off-peak billing.

Hosted weightsReasoningTool callingStructured outputTemperature

Model specifications

Context window
1M tokens
Output limit
384K tokens
Release date
2026-08-12
Input modalities
text
Output modalities
text
Last updated
2026-08-13

Provider pricing

USD per 1M tokens. Limits may differ from the underlying model.

Checked 2026-09-07

DeepSeek API (off-peak)

deepseek-v4-pro

Input
$0.66
Output
$1.98
Context
1M

DeepSeek API (peak)

deepseek-v4-pro

Input
$1.32
Output
$3.96
Context
1M
ProviderModel IDInputOutputContext
DeepSeek API (off-peak)deepseek-v4-pro$0.66$1.981M
DeepSeek API (peak)deepseek-v4-pro$1.32$3.961M

Promotions, plan quotas, cache pricing and regional taxes are not included. Recheck the provider before purchase.

DeepSeek V4 Pro 0813 FAQ

Is DeepSeek V4 Pro 0813 an open-weight model?

No. DeepSeek V4 Pro 0813 is tracked as a hosted model. Access, retention and commercial terms depend on the selected provider.

What is the context window for DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has a tracked context window of 1M tokens and a maximum output of 384K tokens. Provider limits can be lower.

What input does DeepSeek V4 Pro 0813 support?

The current record lists text input and text output. Check the exact provider route before relying on a modality in production.

How much does DeepSeek V4 Pro 0813 cost?

This page compares 2 tracked provider offerings in USD per 1M tokens where public prices are available. Promotions, cache rates, taxes and plan quotas may differ.

Sources

DeepSeek models and pricingThe current official table lists the V4-Pro-0813 route, 1M context, 384K maximum output, supported features, concurrency and peak/off-peak prices. Cache-hit input is $0.022/M off-peak and $0.044/M peak; cache-miss input is $0.66/M off-peak and $1.32/M peak.Models.dev canonical model recordProvides a normalized record for the hosted 0813 snapshot and its capabilities and limits.

Record status

Lab
DeepSeek
Family
DeepSeek V4
Providers shown
2
Last checked
2026-09-07

Related products

DeepSeekDeepSeek V4 API