// AI Platform Drift

DeepSeek V4 Flash prompt pricing dropped 67% on OpenRouter

OpenRouter model catalogue · published 2026-10-09 13:22 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter's deepseek/deepseek-v4-flash model reduced its prompt token price from $0.0173 to $0.0057 per 1M tokens, a 67.1% decrease. Completion pricing remains $1.28 per 1M tokens.
WHY IT MATTERSUsing the captured base rates for deepseek/deepseek-v4-flash, 100M prompt tokens per day cost $1.73 before and $0.57 after, excluding all other charges. High-volume prompt workloads see immediate cost reduction without code changes.
WHAT TO DOReforecast your OpenRouter spend if you route traffic to deepseek/deepseek-v4-flash. Pull October actuals and apply the new rate to your prompt token volume to update your budget.
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
 name: DeepSeek: DeepSeek V4 Flash 0423
-pricing.prompt: 0.0000000173
+pricing.prompt: 0.0000000057
 pricing.completion: 0.00000128
 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 pricing decreased significantly. Direct cost impact for teams using this model.
signalspricing.prompt decreased from 0.0000000173 to 0.0000000057 USD per token · price reduction represents ~67% decrease in prompt token cost · model pricing is a direct operational cost for consumers
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)