// AI Platform Drift

DeepSeek V4.1 Flash pricing dropped 88% prompt, 76% completion

OpenRouter model catalogue · published 2026-09-26 20:44 UTC
WORTH KNOWING BUDGET PRICINGLIMITSMODEL
WHAT CHANGEDOpenRouter pricing for deepseek/deepseek-v4.1-flash changed from $0.0000003 to $0.000000035 per prompt token (88% decrease) and $0.0000012 to $0.00000029 per completion token (76% decrease). Maximum completion tokens reduced from 943,718 to 384,000.
WHY IT MATTERSIf you are using this model, your per-request costs just dropped by roughly 80%. If you rely on generating outputs longer than 384k tokens in a single completion, those requests will now fail or truncate.
WHAT TO DOCheck your usage logs for this model ID. If you are calling it, update your cost projections. If any requests specify max_tokens above 384,000 or rely on the previous 943k limit, cap them at 384,000 or split the generation across multiple calls.
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: 0.0000003
-pricing.completion: 0.0000012
+pricing.prompt: 0.000000035
+pricing.completion: 0.00000029
 context_length: 1048576
-top_provider.max_completion_tokens: 943718
+top_provider.max_completion_tokens: 384000
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 dropped significantly and output token limit reduced substantially, affecting cost and capability planning.
signalsprompt price decreased ~88% · completion price decreased ~76% · max_completion_tokens reduced by ~59%
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)