Qwen4 Max
Qwen4 Max is the flagship model in Alibaba's Qwen4 series.
qwen4-maxReleased 16 Nov 2026 (2 days ago)Pricing
List prices at Alibaba DashScope, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.50 | $4.50 | |
| Cached input 95% off input | $0.075 | 95% off input | |
| Cache write, 5 minutes | $1.88 | ||
| Cache write, 1 hour | $3.00 |
What it costs a month
At Alibaba DashScope list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$659
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$540
- Coding agent1,000 requests a day, 40K in / 2K out, cached$873
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,680
Where to run it
1 host serve Qwen4 Max. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Alibaba DashScopeLab API qwen4-max | $1.50 / $4.50 | qwen4-max |
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
- TextImagesVideo
- Produces
- Text
- Features
- Parallel tool callsPrompt cachingVideo inputBuilt-in web search
- Open weights
- License: Apache-2.0Runtimes: 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
- 11% less
- 33% less
- 44% less
- 91% less
Open-weight picks
- 23% less
- 70% less
- 77% less
- 79% less
Model line
Newer and older versions, at each lab's own price.
- Nov 2026Qwen4 MaxLatest$1.50 / $4.50
- Sep 2026Qwen3.8 Max$2.00 / $6.00
- UndatedQwen 3.8 Max$2.23 / $6.68
- May 2026Qwen3.7 Max$2.50 / $7.50
- May 2026Qwen 3.7 Max$2.07 / $6.21
- Jan 2026Qwen3 MaxNot listed
Call it
Using Alibaba DashScope's API.
from litellm import completion
response = completion(
model="dashscope/qwen4-max",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen4 Max cost?
On Alibaba DashScope, Qwen4 Max costs $1.50 per million input tokens and $4.50 per million output tokens. Cached input costs $0.075 per million tokens.
Which APIs offer Qwen4 Max?
Qwen4 Max runs on 1 API: Alibaba DashScope.
What is Qwen4 Max's context window?
992K tokens, with up to 131K tokens in one reply.
Is Qwen4 Max being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen4 Max?
No. Qwen4 Max is the newest model in its line.
What are cheaper alternatives to Qwen4 Max?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (11% less), Gemini 3.8 Flash on Google AI Studio (33% less) and Inkling on DeepInfra (23% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen4 Max released?
Alibaba Qwen released it on 16 Nov 2026.
What is Qwen4 Max's API model id?
Use qwen4-max with Alibaba DashScope.
Sources
Raw catalog entry for qwen4-max on Alibaba DashScope
{
"cache_creation_input_token_cost": 0.000001875,
"cache_creation_input_token_cost_above_1hr": 0.000003,
"cache_read_input_token_cost": 7.5e-8,
"input_cost_per_token": 0.0000015,
"litellm_provider": "dashscope",
"max_input_tokens": 991808,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000045,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true
}