DeepSeekOpen weights

DeepSeek V4 Pro

DeepSeek V4 Pro is a DeepSeek model from DeepSeek, released in 2026-04. It costs $0.43 / $0.87 per 1M, has a 1M-token context window, and is best for open-weights, cheap-reasoning, cheap-frontier. Last verified 2026-06-11.

Spec sheet

Pricing

Input
$0.435 / 1M
Output
$0.87 / 1M
Cached input
$0.003625 / 1M
Free tier
No

Context & speed

Context window
1M tokens
Max output
384k tokens
Throughput
~70 tok/s
Time to first token
~800 ms
Speed tier
balanced

Capabilities

Tool use
Yes
Structured output
Yes
Prompt caching
Yes
Extended thinking
Yes
Vision input
No
Audio in / out
No
Fine-tuning
Yes

Deployment

Open weights
Yes
On-prem
Yes
HIPAA eligible
No
Zero retention
No
Regions
apac, us

Estimated monthly cost

Assumes typical token shape: 2k input, 600 output per call. Prompt caching is excluded from these figures.

10k calls/mo
$13.92
per month
100k calls/mo
$139.20
per month
1M calls/mo
$1.4k
per month

When to use DeepSeek V4 Pro

Sweet spot

  • open weights
  • cheap reasoning
  • cheap frontier
  • long context cheap

Known trade-offs

  • data-routing via China for hosted API
  • below top-20 on arena leaderboard

Works with

DeepSeek SDKOpenAI-compatible APIOpenRouterOllamavLLMLangChain

FAQ — DeepSeek V4 Pro

How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro costs $0.43 / $0.87 per 1M tokens on the DeepSeek API. Cached input reads cost $0.003625 per 1M, cutting the input bill by roughly 99% on repeat system prompts.

What is the context window of DeepSeek V4 Pro?

DeepSeek V4 Pro has a 1M-token context window with up to 384k tokens of output. That's enough for entire codebases, long transcripts, or multi-document RAG.

Does DeepSeek V4 Pro have a free tier?

No — No free tier on the official API — but at $0.435/$0.87 per 1M it is near-free vs frontier peers.

Is DeepSeek V4 Pro HIPAA / EU / on-prem friendly?

DeepSeek V4 Pro is not HIPAA-eligible, not available in an EU region, and offers open weights for self-hosting. Zero data retention is not available.

What is DeepSeek V4 Pro best for?

DeepSeek V4 Pro is best for open weights, cheap reasoning, cheap frontier, long context cheap. Trade-offs to be aware of: data-routing via China for hosted API; below top-20 on arena leaderboard.

Which tools and SDKs work with DeepSeek V4 Pro?

DeepSeek V4 Pro integrates with DeepSeek SDK, OpenAI-compatible API, OpenRouter, Ollama, vLLM, LangChain. Most major AI frameworks support it either natively or through OpenAI-compatible endpoints.