// AI Platform Drift

DeepSeek V4 Pro 0813 prompt pricing decreased 22.7%

OpenRouter model catalogue · published 2026-10-04 05:55 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter reduced the prompt token price for deepseek/deepseek-v4-pro-0813 from $0.22/M tokens to $0.17/M tokens, effective immediately. Completion pricing remains $4.20/M tokens.
WHY IT MATTERSIf you are running this model in production, your per-request cost just dropped by nearly a quarter on the prompt side. For prompt-heavy workloads (long context, RAG, multi-turn conversations), this compounds quickly.
WHAT TO DOPull current month-to-date spend for this model from your OpenRouter dashboard or logs, recalculate October's forecast with the new rate, and update your budget tracking if this model represents material spend.
Model-reported confidence 95% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
 id: deepseek/deepseek-v4-pro-0813
 name: DeepSeek: DeepSeek V4 Pro 0813
-pricing.prompt: 0.00000022
+pricing.prompt: 0.00000017
 pricing.completion: 0.0000042
 context_length: 1048576
 top_provider.max_completion_tokens: 943718
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.95, needed 0.5
triage reasoningPrompt token price reduced by ~23%. Direct impact on API spend forecasting and budget planning.
signalsprompt pricing decreased · price change quantified (0.00000022 → 0.00000017) · affects cost calculation for engineering teams
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)