// AI Platform Drift

DeepSeek V4 Flash pricing split: prompt down 33.8%, completion up 10.1%

OpenRouter model catalogue · published 2026-10-03 01:38 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter changed pricing for deepseek/deepseek-v4-flash-latest effective now. Prompt tokens dropped from $0.0058/M to $0.0038/M (-33.8%). Completion tokens rose from $0.9480/M to $1.0436/M (+10.1%).
WHY IT MATTERSTotal cost per request increases 9.8-10.1% depending on workload mix. Workloads generating ten completion tokens for every prompt token see the full 10.1% increase. Short-output use cases benefit slightly from the prompt discount.
WHAT TO DORerun cost projections using the new rates. If you generate more than three completion tokens per prompt token, budget for a 10% increase. Pass the revised forecast to whoever owns the API spend line.
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-flash-latest
 name: DeepSeek: DeepSeek V4 Flash Latest
-pricing.prompt: 0.000000005775
-pricing.completion: 0.000000948024
+pricing.prompt: 0.000000003825
+pricing.completion: 0.000001043574
 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 reasoningPricing changes directly affect engineering budget and model selection decisions.
signalsprompt price decreased 33.8% · completion price increased 10.1% · pricing change on active model
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)