DeepSeek V3.2 Speciale

DeepSeek V3.2 Speciale is a temporary, API-only variant of DeepSeek V3.2 with maxed-out reasoning, aimed at hard mathematical and competitive-programming problems.

start building →

compare models

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

input · usd / 1m tok

$0.58

output · usd / 1m tok

$1.68

context window

163.84ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.58
output: $1.68

providers

Azure AI Foundry hosts DeepSeek V3.2 Speciale. 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-v3-2-speciale

creatorDeepSeek
model typeText generation
context window163,840 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releaseddec 1, 2025
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-v3-2-speciale",
    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-v3-2-speciale",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

14.5#71 of 90 models on the gateway

omniscience-17.7#63 of 86
gpqa87.1%#44 of 88
humanity’s last exam28.7%#45 of 89

AIME 202596.7%
LiveCodeBench89.6%
GPQA87.1%
AA-LCR70.0%
IFBench63.9%
Terminal-Bench Hard34.8%
Humanity’s Last Exam28.7%
CritPt7.4%
Tau20.0%

Intelligence Index14.46
Omniscience Index-17.72
intelligence index (API)14.5

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 V3.2 Speciale 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 V3.2 Speciale?

DeepSeek V3.2 Speciale is a temporary, API-only variant of DeepSeek V3.2 with maxed-out reasoning, aimed at hard mathematical and competitive-programming problems. Unlike the standard V3.2 it does not support tool calls and was served through a dedicated endpoint for a limited window.

How much does DeepSeek V3.2 Speciale cost?

DeepSeek V3.2 Speciale costs $0.58 per million input tokens and $1.68 per million output tokens through the Impossibl API. All rates are in USD.

view the pricing table ↑

What is the context length of DeepSeek V3.2 Speciale?

DeepSeek V3.2 Speciale has a 163,840-token context window through the Impossibl API.

What inputs and outputs does DeepSeek V3.2 Speciale support?

DeepSeek V3.2 Speciale accepts text as input. DeepSeek V3.2 Speciale returns text.

How do I use DeepSeek V3.2 Speciale through an API?

DeepSeek V3.2 Speciale is available through the Impossibl API. Use deepseek/deepseek-v3-2-speciale 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 V3.2 Speciale released?

DeepSeek released DeepSeek V3.2 Speciale on December 1, 2025.

Creator release announcement ↗

this page describes DeepSeek V3.2 Speciale 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 →