فا

DeepSeek: DeepSeek V4 Flash 0731

by DeepSeek

deepseek/deepseek-v4-flash-0731
HealthyRank #11Down 1 places on last weekOpen weights

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....

Context

1Mtokens

About 1,498 pages of text at once

Max output

944Ktokens

About 1,348 pages in one answer

Intelligence

—

No score published for this model.

Output speed

69tokens/s

A 500-word answer in about 10.1 s

From public market statistics for this model

First token

0.9s

Reasoning models start later

From public market statistics for this model

Health, 30 days

98.96%

8 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input326,178IRR / 1M tokens
Output652,356IRR / 1M tokens
Reasoning tokensThe output rate652,356IRR / 1M tokens
Cache read65,236IRR / 1M tokens

With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.

What would this model cost you a month?

Monthly cost

41.1MIRR

1.37M IRR a day, 685 IRR each request

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health98.96%

Time to first token1.09 s

Output speed62 tokens/s

Place in the market

By usage across the global model market.

Daily rank#11

Share of the day’s tokens1.8%

Capabilities

Image inputNo
Audio inputNo
Tool callingYes
JSON outputYes
ReasoningReasoning levels: max, high, low, none
Web searchNo
Prompt cacheYes
Makes imagesNo
Open weightsYes
On the free planNo
Input
Text
Output
Text

Parameters it accepts

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Other benchmarks

Coding index69
Agentic index41

Design contests

  • WebsitesElo: 1,236Win rate: 47%
  • UI componentsElo: 1,230Win rate: 47%
  • Code (overall)Elo: 1,228Win rate: 46%
  • Game devElo: 1,207Win rate: 45%
4 moreShow less
  • 3DElo: 1,205Win rate: 49%
  • SVGElo: 1,182Win rate: 45%
  • Data vizElo: 1,180Win rate: 41%
  • ASCII artElo: 1,088Win rate: 33%

Standard tests

  • GPQA DiamondScore: 87%Tasks: 2,178
  • τ-bench Verified AirlineScore: 74%Tasks: 500

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1
Model IDdeepseek/deepseek-v4-flash-0731
API keyCreate one in the dashboard
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)
The full guide in the docs: keys, streaming and errors

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

No peer models found.

Technical specs

ID
deepseek/deepseek-v4-flash-0731
Maker
DeepSeek
Tokenizer
DeepSeek
Released
Jul 31, 2026
Added to IranRouter
Aug 19, 2026
Context
1,048,576 tokens
Max output
943,718 tokens
Weights
deepseek-ai/DeepSeek-V4-Flash-0731

Scores by Artificial Analysis, Design Arena, as of Oct 31, 2026

DeepSeek: DeepSeek V4 Flash 0731One message about 980 IRRStart with this model