DeepSeekReasoning & CodingActive

DeepSeek V4 Pro

DeepSeek's premium V4 API model with thinking and non-thinking modes and a large context window.

Facts Verified
Aug 25, 2026
Status
Active
Profile
Source-backed
Compare ModelOfficial Docs
Context
1M tokens
Max output
384K tokens
API
Available

Specifications

Context
1M tokens
Max output
384K tokens
CompanyDeepSeek
Release DateNot published
StatusActive
License / AvailabilityDirect API available

Capability Map

Verified fields
Reasoning
Supported
Vision
Not published
Audio
Not published
Video
Not published
API
Supported
Open weights
Not published
Input modalities
text
Output: text

Developer API Rates

Public rate
Input / 1M
$0.4350
Output / 1M
$0.8700
Cached $0.003625 / 1M

InputPricePer1M represents the published cache-miss input rate; cachedInputPricePer1M represents the cache-hit input rate.

DeepSeek has announced a future peak/off-peak pricing policy. The effective date remains subject to a later announcement, so the current regular rate is stored here.

Calculate Usage in AI Price Tracker →

Verified Capabilities

  • 1M tokens published context window
  • 384K tokens published maximum output
  • Reasoning support listed by the provider
  • Direct API availability is published

Pricing & Availability Notes

  • InputPricePer1M represents the published cache-miss input rate; cachedInputPricePer1M represents the cache-hit input rate.
  • DeepSeek has announced a future peak/off-peak pricing policy. The effective date remains subject to a later announcement, so the current regular rate is stored here.
Provider API model ID
Use this identifier in the provider API where supported.
deepseek-v4-pro

Sources & Freshness

Verified Aug 25, 2026