DeepSeek V4 Flash
Chatdeepseek/deepseek-v4-flashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek, released on 2026-04-24, with 284B total parameters and 13B activated parameters. It is designed for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance. The model supports tool use (function calling) and prompt caching. Context window: 1M tokens, output: 384K. Pricing is $0.14/M input tokens and $0.28/M output tokens, with cached input reads at $0.0028/M, making it well suited to high-volume production traffic. Available via OpenAI and Anthropic protocols.
Providers
/v1/chat/completions/v1/responses/v1/chat/completionsCode Examples
from openai import OpenAIclient = OpenAI(base_url="https://api.ofox.run/v1",api_key="YOUR_OFOX_API_KEY",)response = client.chat.completions.create(model="deepseek/deepseek-v4-flash",messages=[{"role": "user", "content": "Hello!"}],)print(response.choices[0].message.content)
Uptime & Status
Benchmarks
DeepSeek V4 Flash scores 1438 in the Overall category of the LMArena text leaderboard (style control), ranking #70 of 374 models based on 41,568 human preference votes (updated 2026-07-12).
| Category | Arena Score | 95% CI | Rank | Votes |
|---|---|---|---|---|
| Overall | 1433–1442 | #70 of 374 | 41,568 | |
| Hard Prompts | 1455–1466 | #65 of 374 | 27,503 | |
| Coding | 1476–1489 | #71 of 369 | 12,085 | |
| Math | 1414–1441 | #78 of 362 | 2,133 | |
| Creative Writing | 1401–1418 | #65 of 372 | 6,649 | |
| Instruction Following | 1423–1436 | #66 of 374 | 13,952 | |
| Chinese | 1460–1489 | #73 of 344 | 2,014 |
Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.