Qwen

Qwen: Qwen Max

stable

Qwen Max is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

qwen-maxqwenreleased Apr 3, 2024
ProviderQuick start
Context
32.8K
tokens
Max output
8.2K
tokens
Input
$1.60
per 1M
Output
$6.40
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Qwen
Qwen
32.8K$1.60$6.40

Pricing

ItemPriceUnit
Input$1.60per 1M tokens
Output$6.40per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
qwen-max
Family
qwen
Status
stable
Knowledge
Apr 1, 2024
Released
Apr 3, 2024
Gateway Config
API
v1
Auth
DASHSCOPE_API_KEY
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@qwen/qwen-max",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://dashscope-intl.aliyuncs.com/compatible-mode/v1
Chat completions
https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
Model
qwen-max
Auth env
DASHSCOPE_API_KEY

Qwen Max FAQ

How much does the Qwen Max API cost?

Through Qwen, Qwen Max costs $1.60 per 1M input tokens and $6.40 per 1M output tokens.

What is the context window of Qwen Max?

Qwen Max accepts up to 32.8K tokens of context and returns up to 8.2K output tokens on Qwen.

What can Qwen Max do?

Qwen Max supports chat and function calling. It accepts text input.

How do I call Qwen Max through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @qwen/qwen-max. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.