星海词元星海词元
Ready to build?Get an API key — all models at 50% of the official price →
Home › Integrations › Continue

Continue

~/.continue/config.json

Continue keeps model roles separate: chat, autocomplete and embeddings. Point the chat and autocomplete roles at this endpoint and leave embeddings on your existing provider — the catalogue is text and image generation, not embeddings.

Code

{ "models": [{ "title": "StarSeaAPI", "provider": "openai",
    "model": "glm-5.3-flash", "apiBase": "https://starseaapi.com", "apiKey": "sk-your-key" }] }

Quickstart

01

Create an API key

Sign up, then create a token in the console. A key works across the whole catalogue; scope and quota can be restricted per key.

02

Point your client at the endpoint

Set base_url to https://starseaapi.com/v1 and use the key. Any OpenAI-compatible SDK, IDE or desktop client works.

03

Pick a model

Start with a low-cost tier for prototyping. Every id in the catalogue can be swapped without touching code.

04

Watch cost, not just quality

Output tokens are usually priced at a multiple of input, and reasoning models emit thinking tokens. Keep stable prompt prefixes first so caching applies.

Integrations