Skip to main content
DeepSeek’s frontier model. 1M-token context, frontier-class reasoning, and a price tag that makes proprietary alternatives hard to justify.
Slugdeepseek-v4-pro
ParametersFrontier MoE
Context1,000,000 tokens (1M)
Throughput70 tokens/sec
TTFT320ms
LicenseDeepSeek License
Pricingcogito.decart.ai/models/deepseek-v4-pro

​
Best for

  • Hardest reasoning, mathematical proofs, programming competitions
  • Long-context analysis (full books, large codebases, extensive logs)
  • Research workloads where you’d reach for a frontier closed-model API
client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[...],
)

​
On context cost

The full 1M context is included in the standard token rate — no per-token surcharge for using the long window. Pair with context caching and the economics on RAG workloads get very compelling.