# Qwen3 Coder 480B A35B Instruct API Pricing

As of October 10, 2026, Qwen3 Coder 480B A35B Instruct costs $0.22 per 1M input tokens and $1.80 per 1M output tokens from Google Vertex AI, the lowest of 7 providers, with cache reads at $0.022 per 1M tokens. It has a 262,144-token context window and returns up to 32,768 tokens per response.

- Page: https://models.litellm.ai/models/qwen3-coder-480b-a35b-instruct
- Lab: Alibaba
- LiteLLM model name: `vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas`
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Added to LiteLLM: August 2025
- Deprecation date: October 21, 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 |
|---|---|---|---|---|---|---|---|
| Google Vertex AI | `vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas` | $0.22 | $1.80 | $0.022 | – | – | 256K |
| Amazon Bedrock Mantle | `bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct` | $0.45 | $1.80 | – | – | – | 128K |
| DeepInfra | `deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct` | $0.40 | $1.60 | – | – | – | 256K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct` | $0.45 | $1.80 | – | – | – | 256K |
| Novita AI | `novita/qwen/qwen3-coder-480b-a35b-instruct` | $0.38 | $1.55 | – | – | – | 256K |
| Tensormesh (fp8) | `tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8` | $0.45 | $1.80 | $0 | – | – | 256K |
| Together AI (fp8) | `together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8` | $2.00 | $2.00 | – | – | – | 256K |

## Cost examples

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

- Google Vertex AI: $1.34
- Novita AI: $1.535
- DeepInfra: $1.60
- Amazon Bedrock Mantle: $1.80
- Google Vertex AI batch: $0.67

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

- Google Vertex AI: $2.56
- Novita AI: $4.11
- DeepInfra: $4.32
- Amazon Bedrock Mantle: $4.86

## Features

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

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Qwen3 Coder 480B A35B Instruct cost?

Qwen3 Coder 480B A35B Instruct costs $0.22 per 1M input tokens and $1.80 per 1M output tokens from Google Vertex AI, the lowest of 7 providers, with cache reads at $0.022 per 1M tokens. Batch requests cost $0.11 per 1M input tokens and $0.90 per 1M output tokens.

### What is the context window of Qwen3 Coder 480B A35B Instruct?

Qwen3 Coder 480B A35B Instruct has a 262,144-token context window and returns up to 32,768 tokens per response.

### Which providers offer Qwen3 Coder 480B A35B Instruct?

Qwen3 Coder 480B A35B Instruct is available from 7 providers through LiteLLM: Google Vertex AI, Amazon Bedrock Mantle, DeepInfra, Fireworks AI, Novita AI, Tensormesh and Together AI. The lowest price is on Google Vertex AI.

### How do I call Qwen3 Coder 480B A35B Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", 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 Coder 480B A35B Instruct support?

Qwen3 Coder 480B A35B Instruct supports function calling, parallel tool calls, structured output, reasoning and prompt caching.

### When did LiteLLM add Qwen3 Coder 480B A35B Instruct?

Qwen3 Coder 480B A35B Instruct was added to LiteLLM's model price file in August 2025.

### Is Qwen3 Coder 480B A35B Instruct being deprecated?

Google Vertex AI lists a deprecation date of October 21, 2026 for vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas.

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