Post-Cutoff
Search For AI agents

DeepSeekDeepSeek V4 familyCurrentReasoning modelReleased 24 Apr 2026

DeepSeek-V4-Pro

DeepSeek’s strongest model: long-horizon coding agents, reasoning, 1M-context tasks. Open weights (MIT).

Model iddeepseek-v4-pro

Price$1.32 in, $3.96 out per 1M tokens

Checked29 September 2026

No published training cutoff

At least1,868events since its release on 24 April 2026

83 historic, 427 major. 203 days of news.

DeepSeek doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

7 ways to use DeepSeek-V4-Pro, with the model id each provider expects.

Providers, model ids, endpoints and docs for DeepSeek-V4-Pro
ProviderModel idEndpointDocs
DeepSeek API deepseek-v4-pro https://api.deepseek.com api-docs.deepseek.com
DeepSeek API (Anthropic format) deepseek-v4-pro https://api.deepseek.com/anthropic api-docs.deepseek.com
Alibaba Cloud Model Studio deepseek-v4-pro-0813 alibabacloud.com
OpenRouter deepseek/deepseek-v4-pro-0813 openrouter.ai
OpenRouter (preview 0423) deepseek/deepseek-v4-pro openrouter.ai
Hugging Face huggingface.co
Web app chat.deepseek.com

Pricing

Prices for DeepSeek-V4-Pro
Input$1.32 per 1M tokens
Output$3.96 per 1M tokens
Cache read$0.044 per 1M tokens

As published: “per 1M tokens (USD), peak-hour list price; off-peak is half (input 0.66, output 1.98, cache hit 0.022). Peak = 01:00-04:00 and 06:00-10:00 UTC Mon-Fri”.

Source: api-docs.deepseek.com, checked 29 September 2026.

Specs

Input
Text
Output
Text
Context window
1,000,000 tokens
Max output
384,000 tokens
Open weights
Yes
Licence
MIT
Training cutoff
Not published
Released
24 April 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Open-weight 1.6T MoE with 1M context

    1.6T total / 49B active parameters, MIT license, 1M-token context (paper: ‘Towards Highly Efficient Million-Token Context Intelligence’).

    Source: huggingface.co

  • Agentic GA upgrade (0813)

    Found after launch

    GA release greatly strengthened agent performance in production (e.g. Terminal Bench 2.1 87.9, Toolathlon-Verified 74.1 per DeepSeek).

    Source: api-docs.deepseek.com

  • Reasoning effort low/high/max

    Found after launch

    Thinking mode supports three effort levels; non-thinking mode also available.

    Source: api-docs.deepseek.com

  • Native OpenAI Responses API + Codex

    Found after launch

    DeepSeek API natively speaks the Responses API format and is adapted for Codex; Anthropic Messages format also supported.

    Source: api-docs.deepseek.com

  • DSpark speculative decoding module

    Found after launch

    0813 weights ship with an attached DSpark speculative-decoding module for faster inference.

    Source: huggingface.co

Notes

Preview 2026-04-24, GA snapshot DeepSeek-V4-Pro-0813 on 2026-08-13 (same id deepseek-v4-pro). Text-only (no vision). DeepSeek said service continues past 2026-09-14 until further notice. Knowledge cutoff not published.

curl https://api.deepseek.com/chat/completions \
 -H "Authorization: Bearer $DEEPSEEK_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"deepseek-v4-pro","reasoning_effort":"high","messages":[{"role":"user","content":"Hello"}]}'

Sources: https://api-docs.deepseek.com/quick_start/pricing · https://api-docs.deepseek.com/updates · https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813