// AI Platform Drift

DeepSeek V4.1 Flash pricing cut 64% on prompt, 15% on completion

OpenRouter model catalogue · published 2026-10-17 10:47 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter's deepseek/deepseek-v4.1-flash model pricing changed on 17 October 2026. Captured prompt base rate dropped from $0.04 to $0.0145 per 1M tokens. Captured completion base rate dropped from $0.70 to $0.594 per 1M tokens.
WHY IT MATTERSUsing the captured base rates for deepseek/deepseek-v4.1-flash, 100M prompt tokens per day cost $4.00 before and $1.45 after, excluding all other charges. Using the captured base rates for deepseek/deepseek-v4.1-flash, 100M completion tokens per day cost $70.00 before and $59.40 after, excluding all other charges. Workloads with high prompt volume see the largest reduction: prompt cost decreased 63.7%, while completion cost decreased 15.1%.
WHAT TO DOReforecast your OpenRouter spend if you use deepseek/deepseek-v4.1-flash. To estimate the saved prompt cost for deepseek/deepseek-v4.1-flash in dollars, multiply prompt token volume by 0.0255 and divide by 1,000,000, using the captured base-rate difference in dollars per 1M tokens. To estimate the saved completion cost for deepseek/deepseek-v4.1-flash in dollars, multiply completion token volume by 0.106 and divide by 1,000,000, using the captured base-rate difference in dollars per 1M 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-v4.1-flash
 name: DeepSeek: DeepSeek V4.1 Flash
-pricing.prompt: 0.00000004
-pricing.completion: 0.0000007
+pricing.prompt: 0.0000000145
+pricing.completion: 0.000000594
 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 0.98, needed 0.5
triage reasoningPricing for an active model changed materially. Teams budgeting API costs need this update.
signalspricing.prompt decreased from 0.00000004 to 0.0000000145 USD/token · pricing.completion decreased from 0.0000007 to 0.000000594 USD/token · both price fields changed significantly
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)