MajorDeepSeekDeprecationdeepseek-v4-flash
DeepSeek retires legacy v4-flash models, routes to V4.1-Flash-1017
Legacy model names deepseek-v4-flash and deepseek-v4-flash-vision-exp are now retired; requests are silently served by DeepSeek-V4.1-Flash-1017 and billed at Flash pricing. Users relying on the old model behavior should migrate to deepseek-flash.
Oct 17, 2026 (UTC)Views:3
Impact Assessment
Cost2
Reliability2
Migration4
Quality3
Compliance1
Alternative models
Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching
Candidates with lower listed rates
Mistral NemoMistral
Significant cost savings
$0.02 / $0.03
Stored listed rate / 1M tokens
Listed average about 93% lower
Mistral Nemoopenrouter
Significant cost savings
$0.03 / $0.03
Stored listed rate / 1M tokens
Listed average about 92% lower
Llama Prompt Guard 2 22MGroq
Significant cost savings
$0.03 / $0.03
Stored listed rate / 1M tokens
Listed average about 92% lower
Qwen3-ASR FlashQwen
Significant cost savings
$0.04 / $0.04
Stored listed rate / 1M tokens
Listed average about 91% lower
Voxtral Mini 3B 2507AWS Bedrock
Significant cost savings
$0.04 / $0.04
Stored listed rate / 1M tokens
Listed average about 89% lower
Sources
pricing
DeepSeek Pricing
MODEL VERSION DeepSeek-V4.1-Flash-1017 DeepSeek-V4-Pro-0813
Comments
Loading comments...
AI Cost Optimization
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.