deepseek-v4-pro
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-proLicense
Open weights (MIT)
Pricing
Standard
Input$0.55 / 1M
Output$2.19 / 1M
* Rates are from a third-party aggregator — verify before relying on them. A typical 1,500-token prompt with a 650-token answer costs ≈ $0.002 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withdeepseek-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 & limitations
Strengths
- Excellent cost efficiency
- Strong reasoning
- Open weights
- Good coding
Limitations
- Text-only
- Smaller context than top proprietary flagships
How to test it
- No-code: open chat.deepseek.com and pick deepseek-v4-pro from the model switcher — no API key needed.
- Playground: sign in to the DeepSeek Platform and run prompts in the workbench, then copy the generated code.
- API: create a key in the DeepSeek Platform and call the API (example below).
curl https://api.deepseek.com/chat/completions \
# OpenAI-compatible endpoint
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'