Qwen3.6 Max Preview
qwen3.6-max-previewPricing
List prices at AIHubMix, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.27 | $7.61 | |
| Cached input 90% off input | $0.127 | 90% off input | |
| Cache write, 5 minutes | $1.58 |
What it costs a month
At AIHubMix list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$848
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$609
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,019
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,869
Where to run it
1 host serve Qwen3.6 Max Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AIHubMixGateway qwen3.6-max-preview | $1.27 / $7.61 | qwen3.6-max-preview |
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
- Features
- Prompt cachingBuilt-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 AIHubMix.
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
- 30% less
- 47% less
- 56% less
- 93% less
Open-weight picks
- 21% less
- 40% less
- 70% less
- 72% less
Model line
Newer and older versions, at each lab's own price.
- UndatedQwen3.6 Max PreviewLatest$1.27 / $7.61
- UndatedQwen3 Max PreviewNot listed
Call it
Using AIHubMix's API.
from litellm import completion
response = completion(
model="aihubmix/qwen3.6-max-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen3.6 Max Preview cost?
On AIHubMix, Qwen3.6 Max Preview costs $1.27 per million input tokens and $7.61 per million output tokens. Cached input costs $0.127 per million tokens.
Which APIs offer Qwen3.6 Max Preview?
Qwen3.6 Max Preview runs on 1 API: AIHubMix.
What is Qwen3.6 Max Preview's context window?
262K tokens, with up to 66K tokens in one reply.
Is Qwen3.6 Max Preview being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen3.6 Max Preview?
No. Qwen3.6 Max Preview is the newest model in its line.
What are cheaper alternatives to Qwen3.6 Max Preview?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (30% less), Gemini 3.8 Flash on Google AI Studio (47% less) and Qwen4 Max on Alibaba DashScope (21% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Qwen3.6 Max Preview's API model id?
Use qwen3.6-max-preview with AIHubMix.
Sources
Raw catalog entry for qwen3.6-max-preview on AIHubMix
{
"cache_read_input_token_cost": 1.268e-7,
"cache_creation_input_token_cost": 0.000001585,
"input_cost_per_token": 0.000001268,
"litellm_provider": "aihubmix",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0.000007608,
"source": "https://aihubmix.com/api/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_web_search": true
}