Qwen3 Instruct
Qwen3 Instruct is a mixture-of-experts language model with 235 billion total parameters and 22 billion active parameters, optimized for instruction following, human-preferred alignment, and multilingual understanding across 100+ languages. It is purpose-built for enterprise business logic, conversational AI, and customer-facing applications that require consistent, high-quality outputs without the latency of extended reasoning — supporting native function calling, structured outputs, and a 256K token context window.
Features
Serverless API
Qwen Instruct is available via sciforium' serverless API, where you pay per token. There are several ways to call the sciforium API, including sciforium' Python client, the REST API, or OpenAI's Python client.
DocsOn-demand Deployments
On-demand deployments allow you to use Qwen Instruct on dedicated GPUs with sciforium' high-performance serving stack with high reliability and no rate limits.
Docs