// AI Platform Drift

DeepSeek V4 Flash prompt pricing drops 18%

OpenRouter model catalogue · published 2026-10-10 21:46 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGED~deepseek/deepseek-v4-flash-latest prompt token pricing decreased from $0.0116 to $0.0095 per 1M tokens, effective as of the 10 October 2026 catalogue update. Completion pricing remains $1.28 per 1M tokens.
WHY IT MATTERSUsing the captured base rates for ~deepseek/deepseek-v4-flash-latest, 100M prompt tokens per day cost $1.16 before and $0.95 after, excluding all other charges. High-volume prompt workloads see immediate cost reduction without code changes.
WHAT TO DOReforecast October spend if you route significant prompt volume through this model. To estimate the saved prompt cost for ~deepseek/deepseek-v4-flash-latest in dollars, multiply prompt token volume by 0.0021 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-flash-latest
 name: DeepSeek: DeepSeek V4 Flash Latest
-pricing.prompt: 0.0000000116
+pricing.prompt: 0.0000000095
 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; engineering teams budgeting or optimizing costs need to know.
signalspricing.prompt decreased from 0.0000000116 to 0.0000000095 USD per token · price reduction of ~18% 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)