# QwQ 32B API Pricing

As of October 10, 2026, QwQ 32B costs $0.15 per 1M input tokens and $0.45 per 1M output tokens from Nebius AI Studio, the lowest of 7 providers. It has a 32,768-token context window and returns up to 32,768 tokens per response.

- Page: https://models.litellm.ai/models/qwq-32b
- Lab: Alibaba
- LiteLLM model name: `nebius/Qwen/QwQ-32B`
- Context window: 32,768 tokens
- Max output: 32,768 tokens
- Added to LiteLLM: May 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Nebius AI Studio | `nebius/Qwen/QwQ-32B` | $0.15 | $0.45 | – | – | – | 32K |
| Cloudflare Workers AI | `cloudflare/@cf/qwen/qwq-32b` | $0.66 | $1.00 | – | – | – | 24K |
| DeepInfra | `deepinfra/Qwen/QwQ-32B` | $0.15 | $0.40 | – | – | – | 128K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/qwq-32b` | $0.90 | $0.90 | – | – | – | 128K |
| Hyperbolic | `hyperbolic/Qwen/QwQ-32B` | $0.20 | $0.20 | – | – | – | 128K |
| Nscale | `nscale/Qwen/QwQ-32B` | $0.18 | $0.20 | – | – | – | – |
| Together AI | `together_ai/Qwen/QwQ-32B` | $1.20 | $1.20 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Nebius AI Studio: $0.525
- DeepInfra: $0.50
- Nscale: $0.46
- Hyperbolic: $0.50

## Features

Supported: Function calling, Parallel tool calls, Reasoning.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="nebius/Qwen/QwQ-32B",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does QwQ 32B cost?

QwQ 32B costs $0.15 per 1M input tokens and $0.45 per 1M output tokens from Nebius AI Studio, the lowest of 7 providers.

### What is the context window of QwQ 32B?

QwQ 32B has a 32,768-token context window and returns up to 32,768 tokens per response.

### Which providers offer QwQ 32B?

QwQ 32B is available from 7 providers through LiteLLM: Nebius AI Studio, Cloudflare Workers AI, DeepInfra, Fireworks AI, Hyperbolic, Nscale and Together AI. The lowest price is on Nebius AI Studio.

### How do I call QwQ 32B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="nebius/Qwen/QwQ-32B", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does QwQ 32B support?

QwQ 32B supports function calling, parallel tool calls and reasoning.

### When did LiteLLM add QwQ 32B?

QwQ 32B was added to LiteLLM's model price file in May 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json