DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
At a glance
- Context window
- 1Mtokens
- Max output
- 384Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
Benchmarks
- Intelligence index
- 25
- Coding index
- 52
- Agentic index
- 28
Design Arena
| Category | Elo | Win rate |
|---|---|---|
| models · codecategories | 1,221 | 48.9 |
| models · gamedev | 1,220 | 50.2 |
| models · website | 1,220 | 49.1 |
| models · 3d | 1,216 | 49.3 |
| models · svg | 1,181 | 48.4 |
| models · uicomponent | 1,179 | 44.7 |
| models · dataviz | 1,143 | 40.7 |
| models · asciiart | 1,128 | 42.8 |
Standard evaluations
| Benchmark | Score | Tasks |
|---|---|---|
| gpqa_diamond | 0.87 | 3,366 |
| tau_bench_verified_airline | 0.75 | 1,150 |
Source: Artificial Analysis, Design Arena · as of Sep 16, 2026
Performance
Uptime on IranRouter
12.8%
Reference uptime
100%
Median latency
1,237 ms
Throughput
46.4 tok/s
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Popularity
- Current rank
- #8
- Rank change, 7 days
- -2
Daily tokens · 90 days
770.1B
Ranked by daily token volume across the global model market; the figure above the chart is the daily average.
Supported parameters
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.