DeepSeek V4 Pro

DeepSeek V4 Pro is the large mixture-of-experts flagship of DeepSeek's V4 generation, built for advanced reasoning, coding, and production agent systems.

start building →

compare models

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

input · usd / 1m tok

$1.74

output · usd / 1m tok

$3.48

context window

1mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $1.74
output: $3.48
cache read: $0.145

providers

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

Azure AI Foundry
Azure AI Foundry serving options
endpoint location routes
East US 2 1
East US 1
locations describe provider endpoints; they do not guarantee where inference runs.

Azure AI Foundry serving options
endpoint location	routes
East US 2	1
East US	1

specifications

takes text in, gives text outdeepseek/deepseek-v4-pro

creatorDeepSeek
model typeText generation
context window1,000,000 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releasedapr 24, 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-pro",
    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-pro",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

36.3#25 of 90 models on the gateway

coding index68.8#27 of 60
agentic index42.3#18 of 49
omniscience0.8#36 of 86
gpqa92.8%#15 of 88
humanity’s last exam41.0%#25 of 89
terminal-bench v2.178.7%#23 of 57

GPQA92.8%
AA-LCR80.3%
Terminal-Bench v2.178.7%
AutomationBench Partial56.7%
SciCode51.0%
Humanity’s Last Exam41.0%
Tau Banking39.6%
CritPt18.0%
Multilingual LCR17.8%
Terminal-Bench v4.014.1%
GDP.pdf All-pass11.4%

Intelligence Index36.28
Omniscience Index0.83
GDPval Elo1493.31
coding index (API)68.8
agentic index (API)42.3
intelligence index (API)36.3

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 Pro 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 Pro?

DeepSeek V4 Pro is the large mixture-of-experts flagship of DeepSeek's V4 generation, built for advanced reasoning, coding, and production agent systems. It offers low, high, and max thinking-effort levels, native tool use through the Responses API format, and long-context inputs.

How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro costs $1.74 per million input tokens and $3.48 per million output tokens through the Impossibl API. Cache reads cost $0.145 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of DeepSeek V4 Pro?

DeepSeek V4 Pro has a 1,000,000-token context window through the Impossibl API.

What inputs and outputs does DeepSeek V4 Pro support?

DeepSeek V4 Pro accepts text as input. DeepSeek V4 Pro returns text.

How do I use DeepSeek V4 Pro through an API?

DeepSeek V4 Pro is available through the Impossibl API. Use deepseek/deepseek-v4-pro 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 Pro released?

DeepSeek released DeepSeek V4 Pro on April 24, 2026.

Creator release announcement ↗

this page describes DeepSeek V4 Pro 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 →