GPT OSS 20B

GPT OSS 20B is the smaller of OpenAI's open-weight gpt-oss models, released under Apache 2.0 for local, on-device, and low-latency use.

start building →

compare models

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

input · usd / 1m tok

$0.075

output · usd / 1m tok

$0.30

context window

128ktokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.075
output: $0.30
cache read: $0.0375

providers

Different companies host GPT OSS 20B. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Groq
parasail
Amazon Bedrock

specifications

takes text in, gives text outopenai/gpt-oss-20b

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-20b",
    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-20b",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

10.0#98 of 108 models on the gateway

coding index20.7#57 of 64
agentic index1.2#52 of 53

Intelligence Index9.95
legal index (API)7.3
coding index (API)20.7
agentic index (API)1.2
economics index (API)11.3
engineering index (API)11.7
intelligence index (API)9
strategy and ops index (API)4.8
finance and accounting index (API)7.3
healthcare and medical index (API)6.6

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 20B 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 20B?

GPT OSS 20B is the smaller of OpenAI's open-weight gpt-oss models, released under Apache 2.0 for local, on-device, and low-latency use. It uses a mixture-of-experts design with few active parameters per token, running on consumer hardware where GPT OSS 120B needs a datacenter GPU.

How much does GPT OSS 20B cost?

GPT OSS 20B costs $0.075 per million input tokens and $0.30 per million output tokens through the Impossibl API. Cache reads cost $0.0375 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of GPT OSS 20B?

GPT OSS 20B has a 128,000-token context window through the Impossibl API.

What inputs and outputs does GPT OSS 20B support?

GPT OSS 20B accepts text as input. GPT OSS 20B returns text.

How do I use GPT OSS 20B through an API?

GPT OSS 20B is available through the Impossibl API. Use openai/gpt-oss-20b 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 20B released?

OpenAI released GPT OSS 20B on August 5, 2025.

Creator release announcement ↗

this page describes GPT OSS 20B 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 →