Qwen3 Max API Pricing

As of October 10, 2026, Qwen3 Max costs $1.20 per 1M input tokens and $6.00 per 1M output tokens from DeepInfra, the lowest of 5 providers, with cache reads at $0.24 per 1M tokens. It has a 256,000-token context window and returns up to 65,536 tokens per response.

By AlibabaModel ID deepinfra/Qwen/Qwen3-MaxPrices updated October 10, 2026Checked October 10, 2026

Input: $1.20 / 1M tokens
Output: $6.00 / 1M tokens
Cache read: $0.24 / 1M tokens
Context window: 256,000 tokens
Max output: 65,536 tokens
Providers: 5
Added to LiteLLM: January 2026

Qwen3 Max pricing by provider

8 listings across 5 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Cache read	Context
DeepInfra	`deepinfra/Qwen/Qwen3-Max`	$1.20	$6.00	$0.24	256K
Alibaba Cloud Model Studio	`dashscope/qwen3-max`	–	–	–	252K
Alibaba Cloud Model Studiosnapshot 2026-01-23	`dashscope/qwen3-max-2026-01-23`	–	–	–	252K
Novita AI	`novita/qwen/qwen3-max`	$2.11	$8.45	–	256K
Qianwen AI Platform	`qwen_ai_platform/qwen3-max`	–	–	–	252K
Qianwen AI Platformsnapshot 2026-01-23	`qwen_ai_platform/qwen3-max-2026-01-23`	–	–	–	252K
QwenCloud	`qwencloud/qwen3-max`	–	–	–	252K
QwenCloudsnapshot 2026-01-23	`qwencloud/qwen3-max-2026-01-23`	–	–	–	252K

What Qwen3 Max costs in practice

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

DeepInfra	$5.40
Novita AI	$8.445

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

DeepInfra	$13.20
Novita AI	$22.79

Qwen3 Max features

Function calling
Parallel tool calls
Structured output
Image input
Reasoning
Prompt caching

Use Qwen3 Max with LiteLLM

Call Qwen3 Max through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="deepinfra/Qwen/Qwen3-Max",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: qwen3-max
    litellm_params:
      model: deepinfra/Qwen/Qwen3-Max
      api_key: os.environ/DEEPINFRA_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen3-max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 Max FAQ

How much does Qwen3 Max cost?

Qwen3 Max costs $1.20 per 1M input tokens and $6.00 per 1M output tokens from DeepInfra, the lowest of 5 providers, with cache reads at $0.24 per 1M tokens.

What is the context window of Qwen3 Max?

Qwen3 Max has a 256,000-token context window and returns up to 65,536 tokens per response.

Which providers offer Qwen3 Max?

Qwen3 Max is available from 5 providers through LiteLLM: DeepInfra, Alibaba Cloud Model Studio, Novita AI, Qianwen AI Platform and QwenCloud. The lowest price is on DeepInfra.

How do I call Qwen3 Max with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepinfra/Qwen/Qwen3-Max", 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 Max support?

Qwen3 Max supports function calling, parallel tool calls, structured output, reasoning and prompt caching. It does not support image input.

When did LiteLLM add Qwen3 Max?

Qwen3 Max was added to LiteLLM's model price file in January 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: DeepInfra, Alibaba Cloud Model Studio, Qianwen AI Platform.

Provider pages: DeepInfra, Alibaba Cloud Model Studio, Novita AI, Qianwen AI Platform, QwenCloud.