Qwen 3.8 Max

Alibaba · 1000K token context · text

Pricing: $1.34 per 1M input tokens, $5.35 per 1M output tokens

Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.

Pricing

$1.34 per 1M input tokens and $5.35 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

Prices checked 2026-11-04

Context and limits

The context window is 1,000,000 tokens (1000K).

The maximum output is 131,072 tokens.

When to use Qwen 3.8 Max

Qwen 3.8 Max (model ID `qwen-3-8-max`) takes text input and returns text output.

Supported features in the catalog: function calling (tools), streamed responses over SSE.

Use Qwen 3.8 Max for text generation and chat.

FAQ

How much does Qwen 3.8 Max cost?

$1.34 per 1M input tokens and $5.35 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

What is the context window and output limit of Qwen 3.8 Max?

The context window is 1,000,000 tokens (1000K). The maximum output is 131,072 tokens.

How do I get access to Qwen 3.8 Max?

Create an API key in the llmka.dev dashboard and send requests to model "qwen-3-8-max" at https://api.llmka.dev/v1. The endpoint is OpenAI-compatible. One key and one balance cover all models on the gateway.

Links

All models and prices · API documentation · Quick start

Available through the llmka.dev gateway: OpenAI- and Anthropic-compatible endpoints, one key, USDT top-up.