Qwen3.8-Max

Qwen3.8-Max from Alibaba Cloud Int., served over Claude Messages.

TextClaude MessagesCache Hit Pricing

Context Window

qwen3.8-max

Max Output

1M tokens

Input

$1.8$2.00

10% off

1M tokens

Output

$5.4$6.00

10% off

1M tokens

Model Codeqwen3.8-max

Playground

Model Code

qwen3.8-max

Enter your prompt here...

Output

No output yet

Pricing

Plan	Context Window	Max Output	Input	Output	Cache Write	Cache Read
qwen3.8-max	-	-	$1.8$2.0010% off 1M tokens	$5.4$6.0010% off 1M tokens	$2.25$2.5010% off 1M tokens	$0.225$0.2510% off 1M tokens

Vendor Direct pricing is shown in USD per 1M tokens.

Cache reads use a single $0.25 rate, including 5m; 5m cache creation is $2.50 per 1M tokens.

Cache read or cached input pricing applies to reused prompt tokens.

README

Qwen3.8-Max is a text model from Alibaba Cloud Int., available through the Claude Messages protocol with a uniform cached-input rate and 5-minute cache write pricing.

Qwen3.8-Max is available through the Claude Messages protocol for text generation workloads.
Pricing is $2.00 input, $6.00 output, and a uniform $0.25 cached-input rate per 1M tokens.
5-minute cache creation is $2.50 per 1M tokens.

API

Use the API docs for request format, parameters, and integration details.

Qwen3.8-Max from Alibaba Cloud Int., served over Claude Messages.

Model Code

qwen3.8-max

View API Docs

API

Endpoint

POST /v1/messages

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/messages" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.2
  }'