← Model list

DeepSeek V4 Pro (DeepSeek)

deepseek·deepseek/deepseek-v4-pro-4·GA·Open weights·deepseek-thinking series

Open MoE flagship with million-token context for coding and long agent runs

At a glance
Reference price$0.478 / $0.956 per 1M
Cache read $0.0043 · AIHubMix
Lowest paid$0.435 / $0.87
LLM Gateway Gateway · 1.1× spread
Context1,000,000
⚠ Providers report 1,000,000–1,050,000; the table below is authoritative
Output limit384,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
Text
Knowledge cutoff2025-05
Released / updated2026-04-24 / 2026-04-24

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 2 providers2 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
LLM Gateway
deepseek/deepseek-v4-pro
Gateway$0.435$0.87$0.00361,050,000393,216
AIHubMix
deep-deepseek-v4-pro
Gateway$0.478$0.956$0.00431,000,000384,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1LLM Gateway$78.74
2AIHubMix$86.56
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = higheffort = maxToggle (on / off)

Related models

Price historyone sample accumulated per data sync

Input list $0.478Output list $0.956Min blended $0.544

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-21). Each future sync adds a point, and once accumulated a line is drawn here.