# Qwen3 14B Instruct API Pricing

As of October 10, 2026, Qwen3 14B Instruct costs $0.05 per 1M input tokens and $0.22 per 1M output tokens on Weights & Biases. It has a 32,800-token context window.

- Page: https://models.litellm.ai/models/qwen3-14b-instruct
- Lab: Alibaba
- LiteLLM model name: `wandb/OpenPipe/Qwen3-14B-Instruct`
- Context window: 32,800 tokens
- Added to LiteLLM: August 27, 2026
- Deprecation date: October 5, 2026
- 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 |
|---|---|---|---|---|---|---|---|
| Weights & Biases | `wandb/OpenPipe/Qwen3-14B-Instruct` | $0.05 | $0.22 | – | – | – | 33K |

## Cost examples

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

- Weights & Biases: $0.21

## Features

Supported: none listed.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="wandb/OpenPipe/Qwen3-14B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Qwen3 14B Instruct cost?

Qwen3 14B Instruct costs $0.05 per 1M input tokens and $0.22 per 1M output tokens on Weights & Biases.

### What is the context window of Qwen3 14B Instruct?

Qwen3 14B Instruct has a 32,800-token context window.

### Which providers offer Qwen3 14B Instruct?

Qwen3 14B Instruct is available from Weights & Biases through LiteLLM, using the model name wandb/OpenPipe/Qwen3-14B-Instruct.

### How do I call Qwen3 14B Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="wandb/OpenPipe/Qwen3-14B-Instruct", 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 14B Instruct support?

It does not support image input.

### When did LiteLLM add Qwen3 14B Instruct?

Qwen3 14B Instruct was added to LiteLLM's model price file on August 27, 2026.

### Is Qwen3 14B Instruct being deprecated?

Weights & Biases deprecated wandb/OpenPipe/Qwen3-14B-Instruct on October 5, 2026.

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