DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
Key facts
- Input price
- $0.10 / 1M tokens
- Output price
- $0.30 / 1M tokens
- Context window
- 1M tokens
- Max output
- 944K tokens
- Accepts
- Text
- Returns
- Text
Example: 1,000 requests with 1,000 input and 500 output tokens each would cost about $0.25 (1M input tokens × $0.10 + 0.5M output tokens × $0.30). Estimate your own usage.
Prices are the provider’s own per-token rates with zero markup, from our price list as of Oct 18, 2026. If a call has extra provider charges (images, audio, web search, cached prompts), you pay the reported cost.
Call it from your code
curl https://api.tokenctr.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENCENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek/deepseek-v4-flash-0731", "messages": [{"role": "user", "content": "Hello!"}]}'Works with any OpenAI-compatible SDK: set the base URL to https://api.tokenctr.com/v1. Quickstart
Benchmarks
Artificial Analysis
- Intelligence index
- 34.3
- Coding index
- 69.1
- Agentic index
- 41
Design Arena
| Category | Rank | Elo | Win rate |
|---|---|---|---|
| Models: SVG | 31 | 1183 | 45.1% |
| Models: 3D | 44 | 1209 | 48.7% |
| Models: UI components | 46 | 1235 | 46.8% |
| Models: Websites | 47 | 1239 | 46.7% |
| Models: Code | 49 | 1231 | 46.4% |
| Models: Game dev | 49 | 1211 | 44.6% |
| Models: Data visualization | 62 | 1182 | 41.1% |
| Models: ASCII art | 63 | 1093 | 33.3% |
Source: Artificial Analysis indexes and Design Arena results as published in OpenRouter’s model data, fetched Oct 15, 2026. Higher is better. Not measured by TokenCenter. See all rankings.