DeepSeek V4 Flash 0731 — Benchmark Scores, Pricing & Performance Analysis
DeepSeek V4 Flash 0731 by Alibaba 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.
General Benchmarks
Artificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Coding Benchmarks
Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Reasoning Benchmarks
Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 42 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 9 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 | — |
| Nvidia | $0 | $0 | — | 1.0M | — |
| SCNet Token Plan | $0 | $0 | $0 | 1.0M | — |
| Merge Gateway | $0.035 | $0.07 | $0.007 | 1.0M | — |
| NanoGPT | $0.05 | $0.16 | $0.013 | 1.0M | — |
| Deep Infra | $0.06 | $0.18 | $0.015 | 1.0M | Supported |
| OpenRouter | $0.06 | $0.12 | $0.012 | 1.3M | Supported |
| Vercel AI Gateway | $0.076 | $0.153 | $0.014 | 1.0M | Supported |
| Ambient | $0.08 | $0.18 | $0.016 | 1.0M | — |
| DigitalOcean | $0.08 | $0.252 | $0.0252 | 1.0M | — |
| Cortecs | $0.09 | $0.17 | $0.014 | 1.0M | — |
| Bothub | $0.1 | $0.28 | — | 1.0M | — |
| Baseten | $0.13 | $0.26 | $0.028 | 1.0M | Supported |
| Inceptron | $0.13 | $0.28 | $0.03 | 1.0M | — |
| Perplexity Agent | $0.13 | $0.26 | $0.028 | 1.0M | — |
| RunInfra | $0.13 | $0.27 | $0.01 | 1.0M | — |
| Weights & Biases | $0.13 | $0.28 | $0.07 | 262K | — |
| OpenReason | $0.1371 | $0.2743 | — | 1.0M | — |
| AMD | $0.14 | $0.28 | $0.0028 | 1.0M | — |
| Eden AI | $0.14 | $0.28 | $0.03 | 1.0M | — |
| Hugging Face | $0.14 | $0.28 | — | 1.0M | Supported |
| Nebius Token Factory | $0.14 | $0.28 | $0.14 | 1.0M | — |
| Together AI | $0.14 | $0.28 | $0.03 | 1.0M | Supported |
| AIHubMix | $0.142 | $0.284 | $0.0284 | 1.0M | — |
| OrcaRouter | $0.147 | $0.295 | $0.02 | 1.0M | — |
| GreenPT | $0.1596 | $0.399 | $0.0456 | 1.0M | — |
| Venice AI | $0.175 | $0.35 | $0.035 | 1.0M | — |
| AKI.IO | $0.2 | $0.5 | $0.1 | 1.0M | — |
| Alibaba | $0.2 | $0.4 | $0.04 | 1.0M | Supported |
| Fireworks AI | $0.22 | $0.66 | $0.007 | 1.0M | Supported |
| TensorX | $0.25 | $0.3 | $0.06 | 1.0M | — |
| Requesty | $0.28 | $0.56 | $0.07 | 1.0M | — |
| Tinfoil | $0.3 | $0.7 | $0.06 | 1.0M | — |
| EmpirioLabs AI | $0.424 | $1.272 | $0.424 | 1.0M | — |
| Charm Hyper | $0.44 | $1.32 | $0.044 | 1.0M | — |
| Cloudflare Workers AI | $0.44 | $1.32 | $0.014 | 1.3M | Supported |
| Kilo Gateway | $0.44 | $1.32 | $0.028 | 1.0M | — |
| Ofox | $0.44 | $1.32 | $0.014 | 1.0M | — |
| Volcengine Ark | $0.4453 | $1.3359 | $0.01484 | 1.0M | — |
| Scaleway | $0.468 | $0.936 | $0.0936 | 256K | — |
| Ollama Cloud | — | — | — | 1.0M | — |
DeepSeek V4 Flash 0731 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare DeepSeek V4 Flash 0731 With
DeepSeek V4 Flash 0731 — Frequently Asked Questions
How much does DeepSeek V4 Flash 0731 cost?
DeepSeek V4 Flash 0731 costs $0.06 per 1M input tokens and $0.12 per 1M output tokens. This makes it one of the more affordable models.
What is the context window of DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 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 0731?
DeepSeek V4 Flash 0731 was created by Alibaba. It is classified as a open source model in our catalogue.
Is DeepSeek V4 Flash 0731 open source?
Yes, DeepSeek V4 Flash 0731 is an open-source model. The model weights are publicly available for download and self-hosting.