invokeable()
← directory / models / deepseek-v4-flash

DeepSeek V4 Flash

model deepseek-v4-flash

Draft entry — numbers not yet verified against primary sources.

1M
context
384K
max output
$0.13/M
input
$0.25/M
output
2025-05
knowledge cutoff
2
providers

01Providers

ProviderProvider model IDIn $/MOut $/MContextStatus
DeepSeek API deepseek-v4-flash 0.13 0.25 1M live
OpenRouter deepseek/deepseek-v4-flash 0.13 0.25 1M live

Dimmed prices are canonical — this provider's own quote isn't captured yet.

02Invoke

provider
language

  

  



03Benchmarks · vendor-reported unless verified
SWE-bench Verified (resolved) resolved79




04Related
DeepSeek V4 Pro 08132026-08DeepSeek V4 Flash 07312026-07DeepSeek V4 Pro2026-04DeepSeek V3.22025-09DeepSeek-V3.12025-08DeepSeek V3 03242025-03


05Sources · where these numbers come from
  1. https://github.com/sst/models.dev
  2. https://openrouter.ai/models
  3. https://api-docs.deepseek.com/quick_start/pricing
  4. https://huggingface.co/deepseek-ai
  5. https://api-docs.deepseek.com
  6. https://openrouter.ai/docs
  7. https://openrouter.ai/deepseek/deepseek-v4-flash