IranRouter
All models
DeepSeek

DeepSeek: DeepSeek V4 Pro 0423

Available

by DeepSeek

deepseek/deepseek-v4-proUsage rank #18

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

At a glance

Context window
1Mtokens
Max output
393Ktokens
Knowledge to
Released
2026

Capabilities

CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupportedxhighhigh

Benchmarks

Intelligence index
31
Coding index
59
Agentic index
28

Design Arena

CategoryEloWin rate
models · 3d1,28256.8
models · codecategories1,25651.9
models · gamedev1,25252.3
models · website1,24750.5
models · uicomponent1,23750.6
models · dataviz1,21948.7
models · asciiart1,16746.4
models · svg1,16645.4

Standard evaluations

BenchmarkScoreTasks
gpqa_diamond0.863,561
tau_bench_verified_airline0.761,048

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

Performance

Uptime on IranRouter

0.6%

Aug 18Sep 16

Reference uptime

100%

Aug 18Sep 16

Median latency

1,518 ms

Aug 18Sep 16

Throughput

40.8 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
#18
Rank change, 7 days
+4

Daily tokens · 90 days

329.7B

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_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_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-pro",
    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.