none · low · high · max · default high
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / DEEPSEEK
DeepSeek's higher-capability V4 API model for long-context reasoning, coding and agentic text workloads.
PRIMARY-SOURCE VERIFIED
DeepSeek documents a 1,048,576-token context window. Input modalities: text. Output: text. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Official paid API.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
DeepSeek currently continues API service for DeepSeek V4 Pro; current official documentation supersedes the earlier September 2026 phase-out notice.
DeepSeek publishes time-variable peak and off-peak token rates, so the model is excluded from the fixed-rate calculator.
The current API documentation describes V4 Pro as text-only; no vision capability is asserted.
Knowledge cutoff remains unknown because the cited current official documentation does not publish one.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for DeepSeek V4 Pro since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 1,048,576 context · 393,216 max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head a81376cb9fe2…