DeepSeek · Model identity
DeepSeek V4 Pro
Peak rates are shown by default. Off-peak input, cache-hit, and output charges are 50% lower.
2pricing routes
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateApr 24, 2026
Knowledge cutoffNot independently verified
Open weightsYes
OpenRouter catalog date2026-04-24
First-party metadata verified Aug 26, 2026. Unfilled fields remain unknown. LLMPrice does not infer release dates, knowledge cutoffs, open-weight status, or licenses from a model name, repository link, or pricing route.
| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| Direct APIStandard | deepseek-v4-pro | $1.32 | $0.044 | $3.96 | 1M | Official provider ↗ |
| OpenRouterStandard | deepseek/deepseek-v4-pro | $0.87 | $0.0725 | $1.74 | 1.05M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
Tracking from today forward
No verified price changes have been recorded since tracking began on Aug 26, 2026. Today’s catalog is the baseline; LLMPrice does not invent or backfill older prices.
See all verified price changes →