Models / DeepSeek / DeepSeek V4 Flash
DeepSeek · deepseek-flash
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
$0.14 in · $0.28 out
per 1M tokens · provider rate closest to the median. No first-party DeepSeek price was listed. The reference price is Abacus's rate, the provider closest to the median.
Provider input prices run from $0.035 to $0.50 per 1M tokens. Output prices run from $0.07 to $1.56.
- Context
- 1,000,000
- Max output
- 384,000
- Cache read
- $0.03
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- No
- Open weights
- Yes
- License
- —
- Released
- Apr 24, 2026
- Updated in source
- Apr 24, 2026
- Knowledge
- 2025-05
- Providers
- 52
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Merge Gateway | $0.035 | $0.07 | $0.007 | — | — |
| UnoRouter | $0.063 | $0.13 | — | — | — |
| DevPass | $0.076 | $0.15 | $0.014 | — | — |
| Deep Infra | $0.09 | $0.18 | $0.018 | — | — |
| Kilo Gateway | $0.091 | $0.18 | $0.018 | — | — |
| OpenRouter | $0.091 | $0.18 | $0.018 | — | — |
| TokenGo | $0.098 | $0.20 | $0.028 | — | — |
| Modelis | $0.098 | $0.20 | — | — | — |
| Pioneer | $0.10 | $0.20 | $0.02 | $0.10 | — |
| GMI Cloud | $0.11 | $0.22 | $0.022 | — | — |
| routing.run | $0.11 | $0.22 | — | — | — |
| CrofAI | $0.12 | $0.21 | $0.003 | — | — |
| SiliconFlow | $0.13 | $0.28 | $0.028 | — | — |
| Vercel AI Gateway | $0.13 | $0.26 | $0.028 | — | — |
| Venice AI | $0.14 | $0.28 | $0.028 | — | — |
| Abacusreference | $0.14 | $0.28 | $0.03 | — | — |
| Alibaba | $0.14 | $0.28 | $0.003 | — | — |
| Ambient | $0.14 | $0.28 | $0.028 | $0 | — |
| Auriko | $0.14 | $0.28 | $0.003 | — | — |
| ClinePass | $0.14 | $0.28 | $0.003 | — | — |
| HPC-AI | $0.14 | $0.28 | $0.028 | — | — |
| Hugging Face | $0.14 | $0.28 | — | — | — |
| Jalapeno Cloud | $0.14 | $0.28 | — | — | — |
| NanoGPT | $0.14 | $0.28 | $0.003 | — | — |
| Neuralwatt | $0.14 | $0.28 | $0.028 | — | — |
| Nvidia | $0.14 | $0.28 | $0.003 | — | deprecated |
| SiliconFlow | $0.14 | $0.28 | $0.003 | — | — |
| ZenMux | $0.14 | $0.28 | $0.003 | — | — |
| EBCloud | $0.14 | $0.29 | — | — | — |
| OrcaRouter | $0.15 | $0.30 | $0.02 | — | — |
| ai& | $0.15 | $0.25 | $0.08 | — | — |
| Eden AI | $0.15 | $0.60 | $0.003 | — | — |
| Azure | $0.19 | $0.51 | — | — | — |
| Impossibl | $0.19 | $0.51 | $0.028 | — | — |
| Opper | $0.25 | $0.66 | — | — | — |
| Requesty | $0.28 | $0.56 | $0.07 | — | — |
| CrossModel | $0.30 | $1.20 | $0.006 | $0.30 | — |
| AI/ML API | $0.39 | $1.56 | $0.008 | — | — |
| LLM Gateway | $0.44 | $1.32 | $0.014 | — | — |
| Ofox | $0.44 | $1.32 | $0.014 | — | — |
| Prime Inference | $0.44 | $1.32 | — | — | — |
| Moark | $0.50 | $0.50 | — | — | — |
| AgentRouter | — | — | — | — | — |
| Alibaba Token Plan | $0 | $0 | $0 | $0 | — |
| Alibaba Token Plan | $0 | $0 | $0 | $0 | — |
| AnyAPI | — | — | — | — | — |
| InferX | $0 | $0 | — | — | — |
| Kenari | $0 | $0 | — | — | — |
| Pendra | $0 | $0 | — | — | — |
| SCNet Token Plan | $0 | $0 | $0 | — | — |
| SenseNova | $0 | $0 | $0 | — | — |
| Volcengine Ark Coding Plan | $0 | $0 | $0 | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Long-document Q&A — budget pick on that draft page
- Cheapest summarization — clears the bar
Comparisons
- DeepSeek V4 Flash vs DeepSeek V4 Flash 0731 · DeepSeek
- DeepSeek V4 Flash vs DeepSeek V4 Pro · DeepSeek
- DeepSeek V4 Flash vs DeepSeek V4 Pro 0813 · DeepSeek
- DeepSeek V4 Flash vs DeepSeek V4.1 Flash · DeepSeek