// AI Platform Drift

DeepSeek V4 Flash prompt pricing dropped 63% on OpenRouter

OpenRouter model catalogue · published 2026-10-13 00:42 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter's deepseek/deepseek-v4-flash model reduced its captured prompt base rate from $0.0131 to $0.0048 per 1M tokens, a 63.4% 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 $1.31 before and $0.48 after, excluding all other charges. If you route significant prompt volume through this model, your monthly bill decreases proportionally.
WHAT TO DOPull last month's token usage for deepseek/deepseek-v4-flash from your OpenRouter dashboard or logs, multiply prompt token volume by the 63.4% reduction, and update your cost forecast. If you avoided this model due to price, re-evaluate it against your current routing rules.
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: 0.0000000131
+pricing.prompt: 0.0000000048
 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 0.0000000131 to 0.0000000048 USD per token · price reduction represents ~63% decrease in prompt token cost · model pricing is a direct operational cost for API consumers
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)