Gemini 3.1 Pro (preview)

Gemini 3.1 Pro (preview) is Google's Pro-tier frontier reasoning model, offered in preview for complex problem-solving, agentic coding, and data synthesis.

start building →

compare models

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

input · usd / 1m tok

$2.00

output · usd / 1m tok

$12.00

context window

1mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $2.00over 200k · $4.00
output: $12.00over 200k · $18.00
cache read: $0.20over 200k · $0.40

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

Google hosts Gemini 3.1 Pro (preview). Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Google

specifications

takes text, image, audio and video in, gives text outgoogle/gemini-3.1-pro-preview

creatorGoogle
model typeText generation
context window1,000,000 tokens
maximum outputnot published
input
takes text, image, audio and video in, gives text out
outputtext
tool callingnot verified
releasedfeb 19, 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="google/gemini-3.1-pro-preview",
    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="google/gemini-3.1-pro-preview",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

29.7#47 of 108 models on the gateway

coding index68.8#27 of 64
agentic index8.2#45 of 53
omniscience31.9#4 of 84
gpqa94.1%#3 of 80
humanity’s last exam47.0%#10 of 87

Tau295.6%
GPQA94.1%
MMMU-Pro82.4%
AA-LCR82.0%
IFBench77.1%
SciCode58.7%
Terminal-Bench Hard53.8%
Humanity’s Last Exam47.0%
AnalystAgent41.3%
AutomationBench Partial35.4%
APEX-Agents32.0%
ITBench30.3%
Tau Banking21.4%
GDP.pdf All-pass17.8%
CritPt17.7%
Multilingual LCR15.6%
Harvey LAB0.0%

Intelligence Index29.72
Omniscience Index31.88
GDPval Elo791.33
legal index (API)43.7
coding index (API)68.8
agentic index (API)8.2
economics index (API)44.4
engineering index (API)33
intelligence index (API)29.7
strategy and ops index (API)30
finance and accounting index (API)33.5
healthcare and medical index (API)30.5

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 2026-10-14.

compare Gemini 3.1 Pro (preview) with other models

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

anthropic/claude-opus-5-5$4.00 / $20.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
meta/muse-wonder$4.00 / $20.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →

impossibl models --all →

frequently asked questions

What is Gemini 3.1 Pro (preview)?

Gemini 3.1 Pro (preview) is Google's Pro-tier frontier reasoning model, offered in preview for complex problem-solving, agentic coding, and data synthesis. Over Gemini 3 Pro it delivers a step forward in core reasoning, more reliable agentic behaviour, and leaner token usage.

How much does Gemini 3.1 Pro (preview) cost?

Gemini 3.1 Pro (preview) costs $2.00 per million input tokens and $12.00 per million output tokens through the Impossibl API. Cache reads cost $0.20 per million tokens. These base rates apply through 200,000 total input tokens per request. Above 200,000 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 Gemini 3.1 Pro (preview)?

Gemini 3.1 Pro (preview) has a 1,000,000-token context window through the Impossibl API.

What inputs and outputs does Gemini 3.1 Pro (preview) support?

Gemini 3.1 Pro (preview) accepts text, image, audio, and video as input. Gemini 3.1 Pro (preview) returns text.

How do I use Gemini 3.1 Pro (preview) through an API?

Gemini 3.1 Pro (preview) is available through the Impossibl API. Use google/gemini-3.1-pro-preview 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 Gemini 3.1 Pro (preview) released?

Google released Gemini 3.1 Pro (preview) on February 19, 2026.

Creator release announcement ↗

this page describes Gemini 3.1 Pro (preview) 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 →