DeepSeek V4 Flash by DeepSeek demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
Coding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 65 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Alibaba Token Plan | $0 | $0 | $0 | 1.0M | — |
| Alibaba Token Plan (China) | $0 | $0 | $0 | 1.0M | — |
| InferX | $0 | $0 | — | 1.0M | — |
| Kenari | $0 | $0 | — | 1.0M | — |
| Pendra | $0 | $0 | — | 1.0M | — |
| SCNet Token Plan | $0 | $0 | $0 | 1.0M | — |
| SenseNova (China) | $0 | $0 | $0 | 1.0M | — |
| Umans AI Coding Plan | $0 | $0 | $0 | 1.0M | — |
| Volcengine Ark Coding Plan | $0 | $0 | $0 | 1.0M | — |
| Merge Gateway | $0.035 | $0.07 | $0.007 | 1.0M | — |
| DevPass (LLM Gateway) | $0.05 | $0.1 | $0.01 | 1.1M | — |
| UnoRouter | $0.0625 | $0.125 | — | 1.0M | — |
| DigitalOcean | $0.0679 | $0.168 | $0.0168 | 1.0M | — |
| LLM Gateway | $0.076 | $0.153 | $0.014 | 1.0M | — |
| OpenRouter | $0.088606 | $0.177212 | $0.017721 | 1.0M | Supported |
| Deep Infra | $0.09 | $0.18 | $0.018 | 1.0M | Supported |
| TokenGo | $0.098 | $0.196 | $0.028 | 1.0M | — |
| Modelis | $0.0983 | $0.1966 | — | 1.0M | — |
| Pioneer | $0.1 | $0.2 | $0.0197 | 1.0M | — |
| GMI Cloud | $0.112 | $0.224 | $0.022 | 1.0M | — |
| routing.run | $0.112 | $0.224 | — | 1.0M | — |
| CrofAI | $0.12 | $0.21 | $0.003 | 1.0M | — |
| Vercel AI Gateway | $0.13 | $0.26 | $0.028 | 1.0M | Supported |
| Abacus | $0.14 | $0.28 | $0.03 | 1.0M | — |
| AIHubMix | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Alibaba (China) | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| Ambient | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Arcee | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Auriko | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| ClinePass | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| EmpirioLabs AI | $0.14 | $0.28 | $0.14 | 1.0M | — |
| HPC-AI | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Hugging Face | $0.14 | $0.28 | — | 1.0M | Supported |
| Jalapeno Cloud | $0.14 | $0.28 | — | 1.0M | — |
| Kilo Gateway | $0.14 | $0.28 | $0.028 | 1.0M | — |
| NanoGPT | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| Neuralwatt | $0.14 | $0.28 | $0.028 | 1.0M | — |
| NovitaAI | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Nvidia | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| OpenCode Zen | $0.14 | $0.28 | $0.028 | 1.0M | — |
| SiliconFlow | $0.14 | $0.28 | $0.028 | 1.0M | — |
| SiliconFlow (China) | $0.14 | $0.28 | $0.003 | 1.0M | — |
| Umans AI | $0.14 | $0.28 | $0.028 | 1.0M | — |
| Weights & Biases | $0.14 | $0.28 | $0.07 | 1.0M | — |
| ZenMux | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| EBCloud | $0.143 | $0.2857 | — | 1.0M | — |
| OrcaRouter | $0.147 | $0.295 | $0.02 | 1.0M | — |
| ai& | $0.15 | $0.25 | — | 1.0M | — |
| DeepSeek | $0.15 | $0.6 | $0.003 | 1.0M | Supported |
| OpenCode Go | $0.15 | $0.6 | $0.003 | 1.0M | — |
| TensorX | $0.15 | $0.3 | $0.0375 | 1.0M | — |
| Vivgrid | $0.15 | $0.3 | $0.03 | 1.0M | — |
| above.dev | $0.165 | $0.66 | $0.0033 | 1.0M | — |
| Azure | $0.19 | $0.51 | — | 1.0M | Supported |
| Impossibl | $0.19 | $0.51 | $0.028 | 1.0M | — |
| Charm Hyper | $0.2 | $0.4 | $0.04 | 1.0M | — |
| Vancine | $0.22 | $0.66 | $0.007 | 1.0M | — |
| CrossModel | $0.27 | $1.08 | $0.0054 | 1.0M | — |
| Requesty | $0.28 | $0.56 | $0.07 | 1.0M | — |
| Vultr | $0.3 | $1 | — | 1.0M | — |
| Eden AI | $0.44 | $1.32 | $0.014 | 1.0M | — |
| Ofox | $0.44 | $1.32 | $0.014 | 1.0M | — |
| AgentRouter | — | — | — | 1.0M | — |
| AnyAPI | — | — | — | 1.0M | — |
| Ollama Cloud | — | — | — | 1.0M | — |
DeepSeek V4 Flash — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
DeepSeek V4 Flash — Frequently Asked Questions
How much does DeepSeek V4 Flash cost?
DeepSeek V4 Flash costs $0.04 per 1M input tokens and $0.11 per 1M output tokens. This makes it one of the more affordable models.
What is the context window of DeepSeek V4 Flash?
DeepSeek V4 Flash has a context window of 1.3M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created DeepSeek V4 Flash?
DeepSeek V4 Flash was created by DeepSeek. It is classified as a open source model in our catalogue.
Is DeepSeek V4 Flash open source?
Yes, DeepSeek V4 Flash is an open-source model. The model weights are publicly available for download and self-hosting.