Qwen3-235B-A22B

This documentation is valid for the following list of our models:

Qwen/Qwen3-235B-A22B-fp8-tput

Model Overview

A hybrid instruct-and-reasoning text model built on a sparse mixture-of-experts architecture. It is optimized for high-throughput inference, balancing efficiency, performance, and output quality. This configuration offers the most cost-effective way to handle large workloads, such as batch inference and model distillation.

How to Make a Call

Setup You Can’t Skip

: Visit the AI/ML API website and create an account (if you don’t have one yet). : After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.

Copy the code example

At the bottom of this page, you'll find that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Only model and messages are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding , which lists all available parameters along with notes on how to use them.

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.

If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our .

API Schema

Code Example (Python)

import requests

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"Qwen/Qwen3-235B-A22B-fp8-tput",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello"
            }
        ]
    }
)

data = response.json()
print(data)

Response

{'id': 'ntFB5Ap-6UHjtw-93cab7642d14efac', 'object': 'chat.completion', 'choices': [{'index': 0, 'finish_reason': 'stop', 'logprobs': None, 'message': {'role': 'assistant', 'content': '<think>\nOkay, the user just said "Hello". I should respond in a friendly and welcoming manner. Let me make sure to greet them back and offer assistance. Maybe say something like, "Hello! How can I help you today?" That should be open-ended and inviting for them to ask questions or share what\'s on their mind. Keep it simple and positive.\n</think>\n\nHello! How can I help you today? 😊', 'tool_calls': []}}], 'created': 1746725755, 'model': 'Qwen/Qwen3-235B-A22B-fp8-tput', 'usage': {'prompt_tokens': 4, 'completion_tokens': 111, 'total_tokens': 115}}

PreviousQwen-QwQ-32B NextAnthracite

Last updated 21 days ago

Was this helpful?

Model Overview

How to Make a Call

Setup You Can’t Skip

: Visit the AI/ML API website and create an account (if you don’t have one yet). : After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.

Copy the code example

At the bottom of this page, you'll find that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.

If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our .

Code Example (Python)

import requests

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"Qwen/Qwen3-235B-A22B-fp8-tput",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello"
            }
        ]
    }
)

data = response.json()
print(data)

Response

{'id': 'ntFB5Ap-6UHjtw-93cab7642d14efac', 'object': 'chat.completion', 'choices': [{'index': 0, 'finish_reason': 'stop', 'logprobs': None, 'message': {'role': 'assistant', 'content': '<think>\nOkay, the user just said "Hello". I should respond in a friendly and welcoming manner. Let me make sure to greet them back and offer assistance. Maybe say something like, "Hello! How can I help you today?" That should be open-ended and inviting for them to ask questions or share what\'s on their mind. Keep it simple and positive.\n</think>\n\nHello! How can I help you today? 😊', 'tool_calls': []}}], 'created': 1746725755, 'model': 'Qwen/Qwen3-235B-A22B-fp8-tput', 'usage': {'prompt_tokens': 4, 'completion_tokens': 111, 'total_tokens': 115}}

POST /v1/chat/completions HTTP/1.1 Host: api.aimlapi.com Authorization: Bearer <YOUR_AIMLAPI_KEY> Content-Type: application/json Accept: */* Content-Length: 538 { "model": "Qwen/Qwen3-235B-A22B-fp8-tput", "messages": [ { "role": "system", "content": "text", "name": "text" } ], "max_tokens": 512, "stop": "text", "stream": false, "stream_options": { "include_usage": true }, "n": 1, "seed": 1, "top_p": 1, "top_k": 1, "temperature": 1, "repetition_penalty": 1, "logprobs": true, "echo": true, "min_p": 1, "presence_penalty": 1, "frequency_penalty": 1, "logit_bias": { "ANY_ADDITIONAL_PROPERTY": 1 }, "tools": [ { "type": "function", "function": { "description": "text", "name": "text", "parameters": null } } ], "tool_choice": "none", "response_format": { "type": "text" } }

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Generate a conversational response using a language model.

^_(Optional)Adjust other optional parameters if needed

^_(Optional)Adjust other optional parameters if needed