What

Adds Atlas Cloud as a model provider, wired the same way OrcaRouter is (the most recent comparable addition): a frontend Provider entry, a brand icon, an i18n exception-list entry, and a backend platform mapping. 6 files, +14/-0.

Atlas Cloud (https://api.atlascloud.ai/v1) is an OpenAI-compatible gateway serving open-weight models from DeepSeek, Z.ai, Moonshot, Qwen and MiniMax under one key.

{
  id: 'atlascloud',
  name: 'Atlas Cloud',
  apiKey: '',
  apiHost: 'https://api.atlascloud.ai/v1',
  description: 'Atlas Cloud model configuration.',
  is_valid: false,
  model_type: '',
}

Backend side, same pattern as orcarouter and nebius:

"atlascloud": "openai-compatible-model",

One thing worth noting

The brand icon is @lobehub/icons-static-svg's existing atlascloud.svg, copied verbatim byte-for-byte (including the trailing newline every other icon in src/assets/model/ already has) — no new icon had to be drawn or sourced elsewhere.

Checks

npm run type-check — clean
npm run lint — same 40 problems (33 errors, 7 warnings) as main, none in the files this PR touches
npm run check:i18n — both checks OK (the new description string is in the source-usage exception list)
npx prettier --check on the changed files — clean
Live: GET /v1/models → 200, 117 models; a chat completion against deepseek-ai/deepseek-v4-flash → 200, "EIGENT OK"

/v1/models is public, so that half is re-checkable without a key:

curl -s https://api.atlascloud.ai/v1/models | head -c 300

Disclosure

I work at Atlas Cloud. Happy to adjust the description or position in the list to whatever you prefer.

🤖 Generated with Claude Code

Activity

feat(models): add Atlas Cloud as a model provider

50304dfOct 9