GPT-5.4 nano

GPT-5.4 nano is the lightest, most cost-efficient tier of OpenAI's GPT-5.4 family, optimised for speed-critical and high-volume tasks.

start building →

compare models

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

input · usd / 1m tok

$0.20

output · usd / 1m tok

$1.25

context window

400ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.20
output: $1.25
cache read: $0.02

providers

Different companies host GPT-5.4 nano. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Azure OpenAI
OpenAI

specifications

takes text and image in, gives text outopenai/gpt-5.4-nano

creatorOpenAI
model typeText generation
context window400,000 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
releasedmar 17, 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="openai/gpt-5.4-nano",
    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="openai/gpt-5.4-nano",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

20.7#79 of 113 models on the gateway

coding index56.1#38 of 66
agentic index16.0#42 of 54
omniscience-29.5#75 of 90
gpqa81.7%#55 of 82
humanity’s last exam28.3%#53 of 93

GPQA81.7%
AA-LCR76.7%
Tau276.0%
IFBench75.9%
MMMU-Pro65.4%
SciCode47.2%
Terminal-Bench Hard42.4%
Humanity’s Last Exam28.3%
Tau Banking27.4%
APEX-Agents24.9%
ITBench24.4%
Multilingual LCR16.1%
CritPt9.3%
GDP.pdf All-pass7.8%
AutomationBench Partial6.0%

Intelligence Index20.72
Omniscience Index-29.47
GDPval Elo947.98
legal index (API)22.1
coding index (API)56.1
agentic index (API)16
economics index (API)30.3
engineering index (API)22.7
intelligence index (API)20.7
strategy and ops index (API)15.8
finance and accounting index (API)20.7
healthcare and medical index (API)16.8

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 2026-10-21.

compare GPT-5.4 nano with other models

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

anthropic/claude-opus-5-5$4.00 / $20.00compare →
moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
google/gemini-4-argon$2.00 / $10.00compare →
meta/muse-wonder$4.00 / $20.00compare →

impossibl models --all →

frequently asked questions

What is GPT-5.4 nano?

GPT-5.4 nano is the lightest, most cost-efficient tier of OpenAI's GPT-5.4 family, optimised for speed-critical and high-volume tasks. It supports text and image input and targets low-latency work, trading the depth of GPT-5.4 and GPT-5.4 mini for throughput and price.

How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens through the Impossibl API. Cache reads cost $0.02 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of GPT-5.4 nano?

GPT-5.4 nano has a 400,000-token context window through the Impossibl API.

What inputs and outputs does GPT-5.4 nano support?

GPT-5.4 nano accepts text and image as input. GPT-5.4 nano returns text.

How do I use GPT-5.4 nano through an API?

GPT-5.4 nano is available through the Impossibl API. Use openai/gpt-5.4-nano 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 GPT-5.4 nano released?

OpenAI released GPT-5.4 nano on March 17, 2026.

Creator release announcement ↗

this page describes GPT-5.4 nano 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 →