LLMPrice
Updated daily
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
Context1.05Mlargest published route limit
Max output384Klargest published route limit
InputsTextfrom route metadata
OutputsNot publishedfrom route metadata
Capabilities

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
Model facts

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.

Pricing routes

2 ways this model appears in the catalog

Calculate this model →
Endpoint / routeModel IDInputCachedOutputContextSource
Direct APIStandarddeepseek-v4-pro$1.32$0.044$3.961MOfficial provider ↗
OpenRouterStandarddeepseek/deepseek-v4-pro$0.87$0.0725$1.741.05MOpenRouter API ↗
Published repository IDs

Hugging Face references

Presence of a Hugging Face ID is not treated as proof that model weights are open.

Price history

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 →