// AI Platform Drift

DeepSeek V4 Flash prompt pricing drops 39%

OpenRouter model catalogue · published 2026-10-12 06:00 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDdeepseek/deepseek-v4-flash: captured prompt base rate changed from $0.0216 to $0.0131 per 1M tokens. 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 $2.16 before and $1.31 after, excluding all other charges. To estimate the saved prompt cost for deepseek/deepseek-v4-flash in dollars, multiply prompt token volume by 0.0085 and divide by 1,000,000, using the captured base-rate difference in dollars per 1M tokens.
WHAT TO DOReforecast monthly spend if you are routing traffic to this model. Query your logs for deepseek/deepseek-v4-flash usage over the last 30 days, multiply prompt token volume by the rate difference, and update your budget projection.
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: 0.0000000216
+pricing.prompt: 0.0000000131
 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 materially, directly affecting API costs for users of this model.
signalspricing.prompt decreased from 0.0000000216 to 0.0000000131 USD per token · price reduction of approximately 39% on prompt tokens · model pricing change affects cost calculations for production workloads
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)