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

DeepSeek

DeepSeek V4 API

DeepSeek's current V4 API line, covering V4-Pro and V4-Flash with 1M context, thinking mode and tool calls.

Globally availableFull English UIPublic APIPaid

Quick answer

V4 is the current API line, with separate migration and pricing implications from the broader DeepSeek brand.

PricingDocumentation
Pricing
Off-peak V4-Flash: $0.007/$0.22/$0.66; V4-Pro: $0.022/$0.66/$1.98 per M cache-hit/cache-miss/output tokens; peak rates are double
Availability
Globally available
API
Public API
Last checked
2026-08-17
Pricing detailsUse-case fitSource evidence

The English DeepSeek docs list deepseek-v4-pro and deepseek-v4-flash as the stable public IDs, currently routing to V4-Pro-0813 and V4-Flash-0731. Both support thinking and non-thinking modes, JSON output, tool calls and chat prefix completion; FIM completion is available in non-thinking mode. Billing now varies by peak and off-peak UTC windows while model IDs remain unchanged.

Topic guide

DeepSeek models, API and agent ecosystem

A source-backed map of DeepSeek V4 models, API pricing, native Harness, third-party agent runtimes and practical integration guides.

Editorial verdict

Best for

Developers migrating DeepSeek integrations to current V4 model names and long-context reasoning workflows.

Avoid if

Avoid starting new projects on deepseek-chat or deepseek-reasoner aliases.

Why it matters

V4 is the current API line, with separate migration and pricing implications from the broader DeepSeek brand.

Trust: 3/3 sources verified, recently checkedCoverage: 100/100

Pricing

Off-peak V4-Flash: $0.007/$0.22/$0.66; V4-Pro: $0.022/$0.66/$1.98 per M cache-hit/cache-miss/output tokens; peak rates are double

Payment

Topped-up balance, Granted balance, Platform billing

Commercial use

Commercial use should follow the current product, API, model license and billing terms.

Privacy

Review prompt, file, media upload, retention and training-use terms before sensitive workloads.

Use-case fit

V4 model integration

Strong

Use deepseek-v4-pro for agent/coding tasks and deepseek-v4-flash for faster or lower-cost workloads.

Thinking mode control

Strong

Use the documented thinking toggle and effort controls for reasoning-heavy requests.

Global user checklist

RegistrationConfirmedRequires a DeepSeek Platform API key.
English UIConfirmedQuick start, pricing, guides and change log are English-facing.
API and docsConfirmedDocs cover OpenAI and Anthropic formats plus V4 feature details.
International paymentPartialPricing is clear, but account-specific top-up/payment routes still need verification.

Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.

Pros

  • - 1M context and 384K maximum output are documented
  • - Thinking and non-thinking modes share one current model line
  • - Tool calls, JSON output and context caching are documented
  • - Documented concurrency limits are 2,500 for V4-Flash and 500 for V4-Pro

Cons

  • - Legacy aliases have passed their published deprecation date
  • - Prices can change and are deducted from granted balance before topped-up balance

Decision paths

qwen

kimi-k2-api

zhipu-glm

Sources

DeepSeek models and pricing

Pricing · EN · verified 2026-08-17

Lists the current V4-Pro-0813/V4-Flash-0731 routes, context and output limits, features, concurrency and active peak/off-peak prices.

DeepSeek thinking mode

Documentation · EN · verified 2026-05-17

Documents thinking toggle, effort control and reasoning_content behavior.

DeepSeek change log

Documentation · EN · verified 2026-05-17

Confirms the 2026-04-24 V4 release and 2026-07-24 alias deprecation.

Last checked: 2026-08-17

Reviews

No approved reviews yet.

Availability snapshot

Availability
Globally available
English UI
Full English UI
API
Public API
Rating
4.6 (0)

Latest updates

Latest changes
Release · 2026-08-25

Hermes Agent added with native DeepSeek V4 support

The catalog now tracks Nous Research's Hermes Agent at stable release v0.20.5. Its native DeepSeek provider targets current V4 models, enables thinking by default for V4, preserves required reasoning history across tool calls and migrates retired DeepSeek aliases. A new DeepSeek topic links the models, API, Harness, Hermes setup and runtime comparison.

Release · 2026-08-17

Reasonix 1.26 adds DeepSeek peak/off-peak cost controls

Reasonix 1.26.0 updates its DeepSeek-native coding workflow for the new V4 Flash and V4 Pro peak/off-peak prices. It adds Pro low reasoning effort across OpenAI Chat, Responses and Anthropic modes, unifies cost estimates across CLI, ACP and desktop surfaces, labels peak, off-peak and mixed rates, and automatically migrates configuration to v7.

Pricing · 2026-08-13

DeepSeek routes V4 Pro to 0813 and activates peak/off-peak pricing

DeepSeek's official API now routes deepseek-v4-pro to V4-Pro-0813 and deepseek-v4-flash to V4-Flash-0731. The public model IDs remain unchanged. Peak windows are 01:00-04:00 and 06:00-10:00 UTC; outside those hours, cache-hit, cache-miss and output rates are half the peak rates. Both models retain 1M context, up to 384K output, thinking and non-thinking modes, JSON and tool calls.

Market · 2026-06-23

Microsoft Copilot Cowork GA and usage billing tracked

Microsoft Partner Center says Copilot Cowork became generally available on June 16, 2026 as an agentic system for complex, long-running, multi-tool work inside Microsoft 365. Cowork requires a Microsoft 365 Copilot license and usage-based billing with Copilot Credits, with admin controls for access, budgets and usage. Microsoft lists multiple models, security and compliance capabilities, partner and Dynamics 365 plugins, and a June 30 billing setup deadline for Frontier customers. Axios separately reports Microsoft is considering a Microsoft-hosted DeepSeek option to lower Cowork model costs; this is recorded as a media-reported consideration, not an official model launch.

Submit a review