IranRouter
All models
DeepSeek

DeepSeek: DeepSeek V4 Flash 0731

Available

by DeepSeek

deepseek/deepseek-v4-flash-0731Usage rank #4

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....

At a glance

Context window
1.3Mtokens
Max output
944Ktokens
Knowledge to
Released
2026

Capabilities

CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupportedmaxhighlow

Benchmarks

Intelligence index
35
Coding index
69
Agentic index
42

Design Arena

CategoryEloWin rate
models · uicomponent1,25247
models · website1,25146.8
models · codecategories1,24646.5
models · 3d1,23748.6
models · gamedev1,23344.7
models · svg1,21245.1
models · dataviz1,19741.2
models · asciiart1,11033.3

Standard evaluations

BenchmarkScoreTasks
gpqa_diamond0.851,188
tau_bench_verified_airline0.73300

Source: Artificial Analysis, Design Arena · as of Sep 16, 2026

Performance

Uptime on IranRouter

8.1%

Aug 18Sep 16

Reference uptime

100%

Aug 18Sep 16

Median latency

1,203 ms

Aug 18Sep 16

Throughput

51.3 tok/s

Aug 18Sep 16

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
#4
Rank change, 7 days
0

Daily tokens · 90 days

1.5T

Jun 18Sep 15

Ranked by daily token volume across the global model market; the figure above the chart is the daily average.

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

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-0731",
    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.