Lanseq API

Lanseq provides OpenAI-compatible inference for open-weight models from Hong Kong / APAC infrastructure.

Base URL

https://api.lanseq.cloud/v1

Authentication

Use a Lanseq API key as a Bearer token:

Authorization: Bearer $LANSEQ_API_KEY

Early-access credentials are currently provisioned manually by Lanseq.

Current model

qwen3.8-27b-int4

• Input: text
• Output: text
• Context: 70,000 tokens
• Max output: 8,192 tokens
• Tool calling supported
• Structured / JSON output supported
• Reasoning supported

Pricing

• Input: $0.25 / 1M tokens
• Cached input: $0.045 / 1M tokens
• Output: $1.99 / 1M tokens

Reasoning effort

none | low | medium | xhigh

Additional open-weight model SKUs and capacity are added based on demand.

Provider: Lanseq Technology