Qwen-Turbo

Copied!

Try AIAdd to Compare

ReasoningText Generation

Overview

ReasoningText Generation

Qwen-Turbo is an ultra-large language model that supports multiple input languages such as Chinese and English.Compared to previous versions, the main improvement is in the extended context length. The maximum context length supported by the model has been expanded from 128k to 1M, which is approximately equivalent to 1 million English words or 1.5 million Chinese characters. This is roughly the same as 10 full-length novels, 150 hours of speech transcripts, or 30,000 lines of code.

Input

Text

Output

Text

Features

Prefix Completion

Function Calling

Cache

Structured Outputs

Batches

Web Search

Pricing

Input
$0.05Per 1M tokens
Output
$0.2Per 1M tokens
Input(Thinking)
$0.05Per 1M tokens
Output(Thinking)
$0.5Per 1M tokens
Input(Implicit Cache)
$0.01Per 1M tokens
Input(Thinking Implicit Cache)
$0.01Per 1M tokens
Thinking Output(Batch File)
$0.25Per 1M tokens
Input(Batch File)
$0.025Per 1M tokens
Output(Batch File)
$0.1Per 1M tokens
Input(Thinking Batch File)
$0.025Per 1M tokens

Context

131.07K

Max Input

98.30K

Max Output

8.19K

Rate Limits

RPMRequests Per Minute
600
TPMTokens Per Minute
5M

API Reference

Get API Key

Copied!

123456789101112131415161718192021222324252627282930

from openai import OpenAI
import os

client = OpenAI(
    # If the environment variable is not set, replace it with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you"}]
completion = client.chat.completions.create(
    model="qwen-turbo",  # You can replace this with another deep thinking models
    messages=messages,
    extra_body={"enable_thinking": True},
    stream=True
)
is_answering = False  # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking process" + "=" * 20)
for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20)
            is_answering = True
        print(delta.content, end="", flush=True)

from openai import OpenAI
import os

client = OpenAI(
    # If the environment variable is not set, replace it with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you"}]
completion = client.chat.completions.create(
    model="qwen-turbo",  # You can replace this with another deep thinking models
    messages=messages,
    extra_body={"enable_thinking": True},
    stream=True
)
is_answering = False  # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking process" + "=" * 20)
for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20)
            is_answering = True
        print(delta.content, end="", flush=True)