Grok 4.3

Grok 4.3 is xAI's fast, reliable Grok model built for agentic workflows and instruction-following tasks.

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

input · usd / 1m tok

$1.25

output · usd / 1m tok

$2.50

context window

1mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $1.25over 200k · $2.50
output: $2.50over 200k · $5.00
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

xAI hosts Grok 4.3. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

specifications

takes text and image in, gives text outxai/grok-4.3

creatorxAI
model typeText generation
context window1,000,000 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
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="xai/grok-4.3",
    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="xai/grok-4.3",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

24.9#64 of 108 models on the gateway

coding index42.2#49 of 64
agentic index15.5#43 of 53
omniscience18.0#16 of 84
gpqa90.1%#25 of 80
humanity’s last exam37.2%#31 of 87

Tau297.7%
GPQA90.1%
IFBench81.3%
MMMU-Pro78.1%
AA-LCR73.0%
SciCode48.3%
Terminal-Bench Hard37.9%
Humanity’s Last Exam37.2%
ITBench32.7%
APEX-Agents17.0%
Tau Banking12.4%
Multilingual LCR10.0%
AnalystAgent8.8%
CritPt8.0%
GDP.pdf All-pass5.8%
AutomationBench Partial1.4%

Intelligence Index24.88
Omniscience Index17.98
GDPval Elo937.17
legal index (API)32.3
coding index (API)42.2
agentic index (API)15.5
economics index (API)40.7
engineering index (API)30.7
intelligence index (API)24.9
strategy and ops index (API)16.8
finance and accounting index (API)27
healthcare and medical index (API)26.2

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 Grok 4.3 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 Grok 4.3?

Grok 4.3 is xAI's fast, reliable Grok model built for agentic workflows and instruction-following tasks. It takes text and image inputs, supports function calling and structured outputs, and offers selectable reasoning effort from none to xhigh, defaulting to low so responses stay quick.

How much does Grok 4.3 cost?

Grok 4.3 costs $1.25 per million input tokens and $2.50 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 Grok 4.3?

Grok 4.3 has a 1,000,000-token context window through the Impossibl API.

What inputs and outputs does Grok 4.3 support?

Grok 4.3 accepts text and image as input. Grok 4.3 returns text.

How do I use Grok 4.3 through an API?

Grok 4.3 is available through the Impossibl API. Use xai/grok-4.3 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 →

this page describes Grok 4.3 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 →