// AI Platform Drift

DeepSeek V4.1 Flash prompt pricing increased 549%, completion decreased 50%

OpenRouter model catalogue · published 2026-10-07 06:02 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter's pricing for deepseek/deepseek-v4.1-flash changed on 2026-10-06. The captured prompt base rate changed from $0.003 to $0.019474 per 1M tokens. The captured completion base rate changed from $2.40 to $1.20 per 1M tokens.
WHY IT MATTERSThe asymmetric change means net cost impact depends entirely on your prompt-to-completion ratio. Using the captured base rates for deepseek/deepseek-v4.1-flash, 100M prompt tokens per day cost $0.30 before and $1.9474 after, excluding all other charges. Using the captured base rates for deepseek/deepseek-v4.1-flash, 100M completion tokens per day cost $240.00 before and $120.00 after, excluding all other charges. Workloads generating ten completion tokens for every prompt token see a 49.9% total cost decrease; prompt-heavy workloads with equal token counts see a 49.3% cost decrease.
WHAT TO DOPull your last 30 days of deepseek/deepseek-v4.1-flash usage from OpenRouter logs, calculate your actual prompt-to-completion ratio, and reforecast monthly spend using the new rates. If you generate fewer than three completion tokens per prompt token, evaluate whether a different model now offers better economics.
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: 0.000000003
-pricing.completion: 0.0000024
+pricing.prompt: 0.000000019474
+pricing.completion: 0.0000012
 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 cost calculations for teams building on this model.
signalspricing.prompt increased ~6.5x (0.000000003 → 0.000000019474 USD/token) · pricing.completion decreased ~50% (0.0000024 → 0.0000012 USD/token) · asymmetric price movement across prompt and completion tokens
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)