impulse

Qwen Max

Open weights
API id qwen-max
Input / 1M
$1.60
at Alibaba DashScope
Output / 1M
$6.40
at Alibaba DashScope
Context window
31K
tokens
Max output
8K
tokens per reply
Hosts
4
4 listings
Released
-
date not published

Pricing

List prices at Alibaba DashScope, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.60$6.40

What it costs a month

At Alibaba DashScope list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$960
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$998
  • Coding agent1,000 requests a day, 40K in / 2K out$2,304
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$5,376
Use your own numbers

Where to run it

4 hosts serve Qwen Max. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
qwen-max
$1.60 / $6.40
qwen-max
$1.60 / $6.40
Qwen CloudLab API
qwen-max
$1.60 / $6.40
Fireworks AIInference
qwen-max-latest
$2.00 / $6.00
+7% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Alibaba DashScope.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    29% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    46% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    55% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    93% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    20% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    29% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    38% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    69% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot21.8%

Call it

Using Alibaba DashScope's API.

Python
from litellm import completion

response = completion(
    model="dashscope/qwen-max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen Max cost?

On Alibaba DashScope, Qwen Max costs $1.60 per million input tokens and $6.40 per million output tokens.

Which APIs offer Qwen Max?

Qwen Max runs on 4 APIs: Alibaba DashScope, Qianwen AI Platform, Qwen Cloud and Fireworks AI.

What is Qwen Max's context window?

31K tokens, with up to 8K tokens in one reply.

Is Qwen Max being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Qwen Max?

Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (29% less), Gemini 3.8 Flash on Google AI Studio (46% less) and Qwen4 Max on Alibaba DashScope (20% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Qwen Max's API model id?

Use qwen-max with Alibaba DashScope. Other hosts use their own ids: qwen-max-latest on Fireworks AI.

Sources

Raw catalog entry for qwen-max on Alibaba DashScope
{
  "input_cost_per_token": 0.0000016,
  "litellm_provider": "dashscope",
  "max_input_tokens": 30720,
  "max_output_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 0.0000064,
  "source": "https://www.alibabacloud.com/help/en/model-studio/models",
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_tool_choice": true
}