GPT-5.6 Luna

GPT-5.6 Luna is the fast, cost-efficient tier of OpenAI's GPT-5.6 series, designed for high-volume chat, classification, and lightweight agentic tasks.

start building →

compare models

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

input · usd / 1m tok

$0.20

output · usd / 1m tok

$1.20

context window

1.05mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.20over 272k · $0.40
output: $1.20over 272k · $1.80
cache read: $0.02over 272k · $0.04
cache write · default ttl: $0.25over 272k · $0.50

brackets are by input tokens per request: a request over a threshold is billed at that bracket's rates for all of its tokens. cache creation can have a separate charge.

providers

Different companies host GPT-5.6 Luna. 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-5.6-luna

creatorOpenAI
model typeText generation
context window1,050,000 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
releasedjul 9, 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-5.6-luna",
    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-5.6-luna",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

37.3#36 of 108 models on the gateway

coding index71.4#21 of 64
agentic index42.1#16 of 53
omniscience-10.3#51 of 84
gpqa91.1%#20 of 80
humanity’s last exam39.5%#26 of 87

GPQA91.1%
AA-LCR83.7%
MMMU-Pro78.6%
SciCode53.6%
AutomationBench Partial50.2%
ITBench40.3%
Humanity’s Last Exam39.5%
APEX-Agents35.8%
Tau Banking31.1%
GDP.pdf All-pass24.0%
CritPt20.6%
Multilingual LCR19.4%

Intelligence Index37.32
Omniscience Index-10.28
GDPval Elo1459.40
legal index (API)36.9
coding index (API)71.4
agentic index (API)42.1
economics index (API)42.7
engineering index (API)36.2
intelligence index (API)37.3
strategy and ops index (API)44.1
finance and accounting index (API)40.1
healthcare and medical index (API)35.7

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-5.6 Luna 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-5.6 Luna?

GPT-5.6 Luna is the fast, cost-efficient tier of OpenAI's GPT-5.6 series, designed for high-volume chat, classification, and lightweight agentic tasks. It roughly corresponds to the nano tier of earlier GPT-5 families while keeping text and image input, adjustable reasoning effort, and tool use.

How much does GPT-5.6 Luna cost?

GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens through the Impossibl API. Cache reads cost $0.02 per million tokens; cache writes cost $0.25 per million tokens. These base rates apply through 272,000 total input tokens per request. Above 272,000 input tokens, the long-context rates in the pricing table apply to the whole request. All rates are in USD.

view the pricing table ↑

What is the context length of GPT-5.6 Luna?

GPT-5.6 Luna has a 1,050,000-token context window through the Impossibl API.

What inputs and outputs does GPT-5.6 Luna support?

GPT-5.6 Luna accepts text and image as input. GPT-5.6 Luna returns text.

How do I use GPT-5.6 Luna through an API?

GPT-5.6 Luna is available through the Impossibl API. Use openai/gpt-5.6-luna 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-5.6 Luna released?

OpenAI released GPT-5.6 Luna on July 9, 2026.

Creator release announcement ↗

this page describes GPT-5.6 Luna 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 →