> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ninjachat.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen3 32B

> Qwen's efficient dense 32B model served in fast non-thinking mode with direct tool support.

<div className="ndoc-model-summary">
  <div className="ndoc-model-identity"><span className="ndoc-brand-mark">  <img src="https://cdn.photogenius.ai/new-ai-images/site/v1/landing/marks/marks/44c15113/qwen.svg" alt="" width="32" height="32" /></span><div><strong>Qwen</strong><code>qwen3-32b</code></div></div>
  <div className="ndoc-model-stat"><span>Context window</span><strong>40,960 tokens</strong></div>
</div>

<div className="ndoc-capabilities" aria-label="Model capabilities">
  <span>Streaming</span>
  <span>JSON mode</span>
  <span>Tool calling</span>
  <span>Long context</span>
  <span>Multilingual</span>
</div>

Maximum output: **16,384 tokens**.

## Pricing

| Input         | Output        | Cached input   | Cache write   |
| :------------ | :------------ | :------------- | :------------ |
| \$0.08 / MTok | \$0.28 / MTok | \$0.008 / MTok | \$0.08 / MTok |

Typical request (5K input / 1K output tokens): \~\$0.0007. [Live pricing](https://www.ninjachat.ai/api/v1/models/qwen3-32b).

## Use this model

[Set up your SDK client](/sdks#create-a-client), then run:

<CodeGroup>
  ```typescript TypeScript SDK theme={null}
  const completion = await client.chat.completions.create({
    model: "qwen3-32b",
    messages: [{ role: "user", content: "Explain edge caching in one paragraph." }],
  });

  console.log(completion.choices[0].message.content);
  ```

  ```python Python SDK theme={null}
  completion = client.chat.completions.create(
      model="qwen3-32b",
      messages=[{"role": "user", "content": "Explain edge caching in one paragraph."}],
  )

  print(completion["choices"][0]["message"]["content"])
  ```

  ```bash cURL theme={null}
  curl https://www.ninjachat.ai/api/v1/chat/completions \
    -H "Authorization: Bearer $NINJACHAT_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"model":"qwen3-32b","messages":[{"role":"user","content":"Explain edge caching in one paragraph."}]}'
  ```
</CodeGroup>

## Supported parameters

<div className="ndoc-parameters"><code>messages</code><code>temperature</code><code>max\_completion\_tokens</code><code>top\_p</code><code>stop</code><code>frequency\_penalty</code><code>presence\_penalty</code><code>seed</code><code>stream</code><code>user</code><code>routing</code><code>tools</code><code>tool\_choice</code><code>response\_format</code></div>

Send only parameters from this list. `routing.require_parameters` (default `true`) skips any provider rail that cannot honor every requested parameter, so requests keep the behavior you asked for.

## Routing & fallbacks

Pin `qwen3-32b` with `model` when you want this model's behavior, or list it in an ordered `models` array. With `ninja/auto` first, the router's top pick runs first and `qwen3-32b` is the explicit fallback; `ninja/auto` acts as the router only when it is the first entry.

```json theme={null}
{
  "models": [
    "ninja/auto",
    "qwen3-32b"
  ],
  "messages": [
    {
      "role": "user",
      "content": "Explain edge caching in one paragraph."
    }
  ],
  "routing": {
    "allow_fallbacks": true
  }
}
```

You are billed at the resolved model's token rates, and only for the successful execution.

<Accordion title="Check current availability and limits">
  ```typescript TypeScript SDK theme={null}
  const model = await client.models.retrieve("qwen3-32b");

  if (!model.servable) throw new Error("qwen3-32b is temporarily unavailable");

  console.log({
    contextWindow: model.contextWindow,
    maxOutputTokens: model.maxOutputTokens,
    capabilities: model.capabilities,
    supportedParameters: model.supportedParameters,
    pricing: model.pricing,
    providers: model.providers,
  });
  ```
</Accordion>

**Guides:** [Text generation](/chat) · [Fallbacks](/fallback-chains) · [Smart routing](/smart-routing) · [Pricing](/pricing) · [All models](/models-overview)