# Qwen3 30B A3B API Pricing

As of October 10, 2026, Qwen3 30B A3B costs $0.09 per 1M input tokens and $0.20 per 1M output tokens from Pinstripes, the lowest of 9 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/qwen3-30b-a3b
- Lab: Alibaba
- LiteLLM model name: `pinstripes/ps/qwen3-30b-a3b`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: July 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 |
|---|---|---|---|---|---|---|---|
| Pinstripes | `pinstripes/ps/qwen3-30b-a3b` | $0.09 | $0.20 | – | – | – | 128K |
| Alibaba Cloud Model Studio | `dashscope/qwen3-30b-a3b` | – | – | – | – | – | 126K |
| DeepInfra | `deepinfra/Qwen/Qwen3-30B-A3B` | $0.12 | $0.50 | – | – | – | 40K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b` | $0.15 | $0.60 | – | – | – | 128K |
| Nebius AI Studio | `nebius/Qwen/Qwen3-30B-A3B` | $0.10 | $0.30 | – | – | – | 32K |
| Qianwen AI Platform | `qwen_ai_platform/qwen3-30b-a3b` | – | – | – | – | – | 126K |
| QwenCloud | `qwencloud/qwen3-30b-a3b` | – | – | – | – | – | 126K |
| Cloudflare Workers AI (fp8) | `cloudflare/@cf/qwen/qwen3-30b-a3b-fp8` | $0.0509 | $0.335 | – | – | – | 32K |
| Novita AI (fp8) | `novita/qwen/qwen3-30b-a3b-fp8` | $0.09 | $0.45 | – | – | – | 40K |

## Cost examples

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

- Pinstripes: $0.28
- Nebius AI Studio: $0.35
- DeepInfra: $0.49
- Fireworks AI: $0.60

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Pinstripes: $0.94
- Nebius AI Studio: $1.06
- DeepInfra: $1.30
- Fireworks AI: $1.62

## Features

Supported: Function calling, Reasoning.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="pinstripes/ps/qwen3-30b-a3b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Qwen3 30B A3B cost?

Qwen3 30B A3B costs $0.09 per 1M input tokens and $0.20 per 1M output tokens from Pinstripes, the lowest of 9 providers.

### What is the context window of Qwen3 30B A3B?

Qwen3 30B A3B has a 131,072-token context window and returns up to 131,072 tokens per response.

### Which providers offer Qwen3 30B A3B?

Qwen3 30B A3B is available from 9 providers through LiteLLM: Pinstripes, Alibaba Cloud Model Studio, DeepInfra, Fireworks AI, Nebius AI Studio, Qianwen AI Platform, QwenCloud, Cloudflare Workers AI and Novita AI. The lowest price is on Pinstripes.

### How do I call Qwen3 30B A3B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="pinstripes/ps/qwen3-30b-a3b", 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 30B A3B support?

Qwen3 30B A3B supports function calling and reasoning.

### When did LiteLLM add Qwen3 30B A3B?

Qwen3 30B A3B was added to LiteLLM's model price file in July 2025.

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