GeniusRelay
Sign upConsole

Qwen: Qwen3.6 Max Preview

qwen3.6-max-preview

CompareAPIGet an API keyGet an API key

Qwen3.6 Max Preview costs $1.35 per million input tokens and $8.11 per million output tokens, supports 246K context, and is available through the OpenAI-compatible API.

Qwen3.6 Max Preview is Alibaba's flagship Qwen 3.6 model for complex tasks. It supports both thinking and non-thinking modes in a single model id.

Modalities

Text → Text

Input / output price

$1.35 / $8.11 per 1M

Context

246K · max output 66K

Capabilities

—

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.35
Output$8.11
Cached input$0.676

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0105
Per day
$5.27
Per month (30 days)
$158.18

Qwen3.6 Max Preview: input $1.352/M · output $8.112/M · cached input $0.676/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3.6-max-preview", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to qwen3.6-max-preview.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.6-max-preview",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Qwen3.6 Max Preview billed?
Input is $1.35 and output is $8.11 per million tokens; cached input is $0.676. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
246K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Qwen3.6 Max Preview API pricing · GeniusRelay