DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is the dated snapshot of DeepSeek's efficiency-focused V4 Flash mixture-of-experts model, positioned for coding, reasoning, and agent workflows.

start building →

compare models

                                   . ......           .:-.
                        ... .   ..::-+**=**:.        .-%%*:.
                ..:---+++++--:--+==%@@@@@%*-.       .:=%@%+...                .
           ...-+==%@@@@@#@@@@@@@@##@@##@%+:.        .:%@@@%*-:..            .-+:
          .-*%@#@#@#@#@########@#@@@#@@@%-.         .-%@@@%%@%*-..     ....-*%=+.
       ..:=@##@####@####@@@@##@@@@@##@@@@=-:.       .-%@@@@%@%%%+:..-+****=%%%%+..
      .:+%###@##@@#@#@@##@@@#@@##@#@@#@@@@%*-:       :=%@@@@@%%%%**=%%%%%%%%%%=-.
     .-=@##@@#####@##@###@#@@@#@#@@@@@@@@@@@@=-:.    :+%@@@%@@@%%%%@@%%%%%%%%%*:
   ..-=###@#@#@#####@@#@####@@#@@@@@@@@@@@@@@@@*-..  .:*%%@@@@%@@%@%@%%%@%%%%*:..
   .-%@#@@@####@@##@@###@##@#@@@@#@@@@@@@@@@@@@@%*:.  .:+%%@%%%%@@@@@@%%%%%=*:..
  .:=@#@#@#@@######@@#@##@@@##@@@@@@@@@@@@@@@@@@@%=+:.  :-*%%@%%%%%@%%%%%==-.
  :+@@#@###@#@@@@@@##@@#@#@##@@@@@@@@@@@@@@@@@@@@@@%*-.. ..+%%%@@%%%%%=**-.
 .-%@@##@@@@%@@@@@#@@#@#@@@@@@@@@@@@@@@@@@@@@@@@%%%@%%*::.:-%@%@%%=*--:..
..+@#@@%+-:::::-+**=%@@@@@#@@@@@@@@@@@@@@@@@%%%@@@@%%%%%=*+=%@%%%%=+..
 :*@@#@=- .    .. .::-*%@@@@@@@@@@@@@@@@@@%*+-*=%@@@@%%%%%%%%%%%%%=-.
 :=@#@@%-.           ...:*%@@@@@@@@@@@@@@@%*+::.-*%%%@@@%%%%@%%%%%=:
.:=@@@@%-.               .:-=@@@@@@@@@@@@%%==%+...-%%%@%@%%%%%%%%%*:
 :=@##@@*.                 .:-=@@@@@@@@@@@@*=%*:. .-=%%@@@%%%%%%%=:.
..*@#@@@%:.                  ..+%@@@@@@@%%@%%%=:.  .-=%%%%%%%%%%=*..
 .+@##@@@+:                    .:*%@@@@@@@%@%%%*:...:+%%%%%%%%%%=-..
 .:%@#@@@%:.                    ..+%@@@%%%@@%%%%%****%%%%%%%%%%=*.
  .*@@@#@@=:.                     .-%%%%%%%@%@%%%%%%%%%%%%%%%%%=:.
  .-%@@@#@@*:.                     .:=%@@%@%%@%%%%%%%%%%%%%%%==-.
  ..+@@@@@@@*:.                    ..:*%%@%%@%%%%@%%%%%%%%%%==-.
   .:*%@@#@@@=:.           ... .     ..*%%%%%%@%%%%%%%%%%%==*-.
    .:*@@@@@@@=-:        ..-*+-...     :+=%%%%%%%%%%%%%%%%=*:.
    ..:*@@@@@@@%*:..     ..+%%%=*-:     :-=%%%%%%%%%%%%===+:.
       :+%@@@@@@%%+:.     .-=%%%%%*+:.  ..:*%%%%%%%%%%%==-..
        .-=@@@@@@%@%*-.....:+%%%@%%%=+:..  .-=%%%%%%%%%==++-....
         .:+%%@@@@@@%%=*+--+=%%%%%%%%%%+::...:+*%%=%==%=%===*+-.
           .:*%%%@@@@@%@%%%%%%%%@%%%%%%%%*++----*=%%=%%=%====**-.
             .:+=%%%@%@@@@%@%%@%%@%%%%%%%%%%====*+--+****=***+-.
               .:-*=%%%%%@%@@%@%%%%%%%%%%%%%==*+:............. .
                  .:-+*=%%%%%%%%%%%%%%%==%=*+:.
                    ....:-++***=******+--:..
                             .........

input · usd / 1m tok

$0.14

output · usd / 1m tok

$0.28

context window

1.05mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.14
output: $0.28
cache read: $0.028

providers

Azure AI Foundry hosts DeepSeek V4 Flash 0731. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Azure AI Foundry

specifications

takes text in, gives text outdeepseek/deepseek-v4-flash-0731

creatorDeepSeek
model typeText generation
context window1,048,576 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releasedjul 31, 2026
endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="deepseek/deepseek-v4-flash-0731",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="deepseek/deepseek-v4-flash-0731",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

34.5#27 of 90 models on the gateway

coding index69.1#25 of 60
agentic index41.7#21 of 49
omniscience-14.3#55 of 86
gpqa90.8%#31 of 88
humanity’s last exam38.6%#33 of 89
terminal-bench v2.178.7%#23 of 57

GPQA90.8%
AA-LCR79.7%
Terminal-Bench v2.178.7%
AutomationBench Partial54.0%
SciCode50.3%
Tau Banking39.4%
Humanity’s Last Exam38.6%
CritPt16.6%
Multilingual LCR13.3%
Terminal-Bench v4.012.1%
GDP.pdf All-pass11.0%

Intelligence Index34.53
Omniscience Index-14.28
GDPval Elo1467.78
coding index (API)69.1
agentic index (API)41.7
intelligence index (API)34.5

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-09-11.

compare DeepSeek V4 Flash 0731 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

anthropic/claude-fable-5-1$10.00 / $50.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
meta/muse-spark-1.3$1.25 / $4.25compare →
zai/glm-5.3$1.40 / $4.40compare →

impossibl models --all →

frequently asked questions

What is DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is the dated snapshot of DeepSeek's efficiency-focused V4 Flash mixture-of-experts model, positioned for coding, reasoning, and agent workflows. It is the official release that followed the V4 preview, keeping the same architecture and size but re-post-trained, with native support for the Responses API format.

How much does DeepSeek V4 Flash 0731 cost?

DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens through the Impossibl API. Cache reads cost $0.028 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 has a 1,048,576-token context window through the Impossibl API.

What inputs and outputs does DeepSeek V4 Flash 0731 support?

DeepSeek V4 Flash 0731 accepts text as input. DeepSeek V4 Flash 0731 returns text.

How do I use DeepSeek V4 Flash 0731 through an API?

DeepSeek V4 Flash 0731 is available through the Impossibl API. Use deepseek/deepseek-v4-flash-0731 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was DeepSeek V4 Flash 0731 released?

DeepSeek released DeepSeek V4 Flash 0731 on July 31, 2026.

Creator release announcement ↗

this page describes DeepSeek V4 Flash 0731 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →