GPT OSS 120B

GPT OSS 120B is OpenAI's open-weight mixture-of-experts language model, released under Apache 2.0 for high-reasoning, agentic, and general-purpose production use.

start building →

compare models

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

input · usd / 1m tok

$0.35

output · usd / 1m tok

$0.75

context window

128ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.35
output: $0.75

providers

Different companies host GPT OSS 120B. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Groq
Fireworks
parasail
Cerebras

specifications

takes text in, gives text outopenai/gpt-oss-120b

creatorOpenAI
model typeText generation
context window128,000 tokens
maximum outputnot published
input
takes text in, gives text out
outputtext
tool callingnot verified
releasedaug 5, 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="openai/gpt-oss-120b",
    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-oss-120b",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

11.6#95 of 108 models on the gateway

coding index30.4#54 of 64
agentic index3.7#48 of 53

Intelligence Index11.60
legal index (API)11.3
coding index (API)30.4
agentic index (API)3.7
economics index (API)18.3
engineering index (API)15.1
intelligence index (API)11.6
strategy and ops index (API)7.9
finance and accounting index (API)12.2
healthcare and medical index (API)10.7

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 2026-10-14.

compare GPT OSS 120B with other models

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

anthropic/claude-opus-5-5$4.00 / $20.00compare →
google/gemini-4-argon$2.00 / $10.00compare →
meta/muse-wonder$4.00 / $20.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →

impossibl models --all →

frequently asked questions

What is GPT OSS 120B?

GPT OSS 120B is OpenAI's open-weight mixture-of-experts language model, released under Apache 2.0 for high-reasoning, agentic, and general-purpose production use. It is the larger of the two gpt-oss models, activating a small fraction of its parameters per token and running on a single 80 GB GPU.

How much does GPT OSS 120B cost?

GPT OSS 120B costs $0.35 per million input tokens and $0.75 per million output tokens through the Impossibl API. All rates are in USD.

view the pricing table ↑

What is the context length of GPT OSS 120B?

GPT OSS 120B has a 128,000-token context window through the Impossibl API.

What inputs and outputs does GPT OSS 120B support?

GPT OSS 120B accepts text as input. GPT OSS 120B returns text.

How do I use GPT OSS 120B through an API?

GPT OSS 120B is available through the Impossibl API. Use openai/gpt-oss-120b 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 OSS 120B released?

OpenAI released GPT OSS 120B on August 5, 2025.

Creator release announcement ↗

this page describes GPT OSS 120B 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 →