# Qwen3 32B API Pricing

As of October 10, 2026, Qwen3 32B costs $0.08 per 1M input tokens and $0.23 per 1M output tokens from OVHcloud, the lowest of 11 providers. It has a 32,000-token context window and returns up to 32,000 tokens per response.

- Page: https://models.litellm.ai/models/qwen3-32b
- Lab: Alibaba
- LiteLLM model name: `ovhcloud/Qwen3-32B`
- Context window: 32,000 tokens
- Max output: 32,000 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 |
|---|---|---|---|---|---|---|---|
| OVHcloud | `ovhcloud/Qwen3-32B` | $0.08 | $0.23 | – | – | – | 32K |
| Amazon Bedrock | `qwen.qwen3-32b-v1:0` | $0.15 | $0.60 | – | – | – | 32K |
| Amazon Bedrock Mantle | `bedrock_mantle/qwen.qwen3-32b` | $0.15 | $0.60 | – | – | – | 32K |
| Cerebras | `cerebras/qwen-3-32b` | $0.40 | $0.80 | – | – | – | 128K |
| DeepInfra | `deepinfra/Qwen/Qwen3-32B` | $0.08 | $0.28 | – | – | – | 40K |
| Fireworks AI † | `fireworks_ai/accounts/fireworks/models/qwen3-32b` | $0.90 | $0.90 | – | – | – | 128K |
| GradientAI | `gradient_ai/alibaba-qwen3-32b` | – | – | – | – | – | 128K |
| Nebius AI Studio | `nebius/Qwen/Qwen3-32B` | $0.10 | $0.30 | – | – | – | 40K |
| Vercel AI Gateway | `vercel_ai_gateway/alibaba/qwen-3-32b` | $0.10 | $0.30 | – | – | – | 40K |
| Lambda (fp8) | `lambda_ai/qwen3-32b-fp8` | $0.05 | $0.10 | – | – | – | 128K |
| Novita AI (fp8) | `novita/qwen/qwen3-32b-fp8` | $0.10 | $0.45 | – | – | – | 40K |

† Differs from other providers by more than 8x; check the provider's pricing page.

## Cost examples

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

- OVHcloud: $0.275
- DeepInfra: $0.30
- Nebius AI Studio: $0.35
- Vercel AI Gateway: $0.35

## Features

Supported: Function calling, Parallel tool calls, Structured output, Reasoning.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="ovhcloud/Qwen3-32B",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Qwen3 32B cost?

Qwen3 32B costs $0.08 per 1M input tokens and $0.23 per 1M output tokens from OVHcloud, the lowest of 11 providers.

### What is the context window of Qwen3 32B?

Qwen3 32B has a 32,000-token context window and returns up to 32,000 tokens per response.

### Which providers offer Qwen3 32B?

Qwen3 32B is available from 11 providers through LiteLLM: OVHcloud, Amazon Bedrock, Amazon Bedrock Mantle, Cerebras, DeepInfra, Fireworks AI, GradientAI, Nebius AI Studio, Vercel AI Gateway, Lambda and Novita AI. The lowest price is on OVHcloud.

### How do I call Qwen3 32B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="ovhcloud/Qwen3-32B", 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 Qwen3 32B support?

Qwen3 32B supports function calling, parallel tool calls, structured output and reasoning.

### When did LiteLLM add Qwen3 32B?

Qwen3 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