// AI Platform Drift

DeepSeek V4 Pro 0813 pricing changed: prompt down 67%, completion up 112%

OpenRouter model catalogue · published 2026-10-03 16:19 UTC
ACTION NEEDED BUDGET PRICINGLIMITSMODEL
WHAT CHANGEDOpenRouter updated pricing for deepseek/deepseek-v4-pro-0813 on 3 October 2026. Prompt tokens dropped from $0.66/M to $0.22/M. Completion tokens rose from $1.98/M to $4.20/M. Maximum completion tokens increased from 393,216 to 943,718.
WHY IT MATTERSTotal cost per request increases 67-106% depending on your completion-to-prompt ratio. Workloads generating ten completion tokens per prompt token see costs double. The higher completion limit enables longer outputs but at the new rate.
WHAT TO DOPull last 30 days of request logs for this model. Calculate your actual prompt-to-completion ratio. Multiply completion token volume by the new rate to forecast October spend. If the increase exceeds budget, evaluate alternative models or reduce max_tokens.
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: 0.00000066
-pricing.completion: 0.00000198
+pricing.prompt: 0.00000022
+pricing.completion: 0.0000042
 context_length: 1048576
-top_provider.max_completion_tokens: 393216
+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 0.98, needed 0.5
triage reasoningPricing and token limits changed significantly for an active model.
signalsprompt price decreased 66% · completion price increased 112% · max_completion_tokens increased 140%
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)