Qwen3-32B

Preview

qwen/qwen3-32b

Try it in Playground

TOKEN SPEED

~400 TPS

INPUT

Text

OUTPUT

Text

CAPABILITIES

Tool Use, JSON Mode, Reasoning

Alibaba Cloud

model card

Qwen 3 32B is the latest generation of large language models in the Qwen series, offering groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support. It uniquely supports seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within a single model. The model excels in human preference alignment, creative writing, role-playing, and multi-turn dialogues, while supporting 100+ languages and dialects.

---

PRICING

Input

$0.29

3.4M / $1

Output

$0.59

1.7M / $1

---

LIMITS

CONTEXT WINDOW

131,072

---

MAX OUTPUT TOKENS

40,960

---

Key Technical Specifications

Best Practices

• Mode Selection: Use thinking mode (reasoning_effort="default") for complex reasoning with temperature=0.6, top_p=0.95, top_k=20, and min_p=0
• Non-thinking Mode: For general dialogue, use temperature=0.7, top_p=0.8, top_k=20, and min_p=0
• Math Problems: Include 'Please reason step by step, and put your final answer within \boxed{}' in the prompt
• Multiple-Choice: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g., "answer": "C"."
• History Management: In multi-turn conversations, only include final outputs without thinking content
• Reasoning format: Set reasoning_format to hidden to only return the final answer, or parsed to include the reasoning in a separate field

Get Started with Qwen 3 32B

Experience state-of-the-art language understanding and generation with Qwen 3 32B with Groq speed:

pip install groq

from groq import Groq
client = Groq()
completion = client.chat.completions.create(
    model="qwen/qwen3-32b",
    messages=[
        {
            "role": "user",
            "content": "Explain why fast inference is critical for reasoning models"
        }
    ]
)
print(completion.choices[0].message.content)