// AI Platform Drift

DeepSeek V4 Flash prompt pricing reduced 19.1% on OpenRouter

OpenRouter model catalogue · published 2026-10-04 05:56 UTC
WORTH KNOWING BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter reduced prompt token pricing for deepseek/deepseek-v4-flash-latest from $0.0188/M tokens to $0.0152/M tokens, effective now. Completion pricing remains $1.28/M tokens.
WHY IT MATTERSIf you are routing requests through OpenRouter to this model, your prompt costs dropped by roughly one-fifth. This affects budget forecasts and may change the economics of which model you route to for prompt-heavy workloads.
WHAT TO DOPull last month's token usage for this model from OpenRouter's dashboard, recalculate expected monthly cost with the new rate, and update your budget forecast if the difference is material to your allocation.
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: 0.0000000188
+pricing.prompt: 0.0000000152
 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 price decreased from $0.0000000188 to $0.0000000152 per token. Teams budgeting API costs need to know.
signalsprice decreased · prompt token pricing reduced by ~19% · pricing change on active model
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)