---
title: "deepseek-v4-pro — LLM-TEST.com"
url: /models/deepseek-v4-pro/
canonical_url: https://llm-test.com/models/deepseek-v4-pro/
language: en
type: model
summary: "DeepSeek's open-weight flagship, pairing strong reasoning and coding with exceptional cost efficiency. A standout for teams that want frontier-adjacent capability they can also self-host under MIT."
last_updated: "2026-11-05"
---

# deepseek-v4-pro

_DeepSeek · Flagship · open weights_

DeepSeek's open-weight flagship, pairing strong reasoning and coding with exceptional cost efficiency. A standout for teams that want frontier-adjacent capability they can also self-host under MIT.

## At a glance

- Released: Sep 5, 2026
- Provider: DeepSeek
- Context window: 256,000 tokens
- Max output: 64,000 tokens
- Modalities: Text → text
- Knowledge cutoff: May 2026
- API model ID: `deepseek-v4-pro`
- License: Open weights (MIT)

## Pricing

- Standard: $0.55 input / $2.19 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.002 (standard)

## What's new vs deepseek-v3-pro (February 2026)

- Stronger reasoning and coding than v3-pro
- Larger context window
- Improved efficiency keeping costs very low
- Remains text-only, no image input

## Best use cases

- **Cost-efficient reasoning** — Delivers strong problem-solving at a fraction of frontier prices.
- **Agentic coding** — Plans and writes code across projects affordably.
- **Self-hosted deployment** — Open weights enable private, on-prem serving.

## Strengths

- Excellent cost efficiency
- Strong reasoning
- Open weights
- Good coding

## Limitations

- Text-only
- Smaller context than top proprietary flagships

## Where to get access

- Consumer app: DeepSeek app (web, iOS, Android) — https://chat.deepseek.com
- API: the DeepSeek Platform — https://platform.deepseek.com
- Also available: open weights on Hugging Face
- Docs: https://api-docs.deepseek.com

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/