Hunyuan 4

Hunyuan 4 is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters and the GA successor to Hunyuan 4 Preview, adding image understanding and stronger long-horizon agentic work.

start building →

compare models

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

input · usd / 1m tok

$0.417

output · usd / 1m tok

$1.2505

context window

1.05mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $0.417
output: $1.2505
cache read: $0.021

providers

Tencent hosts Hunyuan 4. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Tencent

specifications

takes text and image in, gives text outtencent/hy4

creatorTencent
model typeText generation
context window1,048,576 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
releasednov 4, 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="tencent/hy4",
    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="tencent/hy4",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

benchmark results are not available for this model yet.

compare Hunyuan 4 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 →
moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
meta/muse-wonder$4.00 / $20.00compare →

impossibl models --all →

frequently asked questions

What is Hunyuan 4?

Hunyuan 4 is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters and the GA successor to Hunyuan 4 Preview, adding image understanding and stronger long-horizon agentic work. It has a one-million-token window of up to 960K input and 64K output, reasons at high effort by default, and can turn thinking off.

How much does Hunyuan 4 cost?

Hunyuan 4 costs $0.417 per million input tokens and $1.2505 per million output tokens through the Impossibl API. Cache reads cost $0.021 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Hunyuan 4?

Hunyuan 4 has a 1,048,576-token context window through the Impossibl API.

What inputs and outputs does Hunyuan 4 support?

Hunyuan 4 accepts text and image as input. Hunyuan 4 returns text.

How do I use Hunyuan 4 through an API?

Hunyuan 4 is available through the Impossibl API. Use tencent/hy4 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 Hunyuan 4 released?

Tencent released Hunyuan 4 on November 4, 2026.

Creator release announcement ↗

this page describes Hunyuan 4 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 →