Skip to content

About

Use your Modelflare models in the VS Code chat model picker.

Resources

Stars

0 stars

Watchers

0 watching

Forks

 
 

Repository files navigation

Modelflare for VS Code

Use every model available to your Modelflare Smart API Key — GPT, Claude, Gemini and more — in the VS Code chat model picker. Bring your own key; no Copilot subscription is required for BYOK models.

一个 Modelflare Smart API Key,在 VS Code 聊天的模型选择器里调用你账号可用的全部模型。

Get a Smart API Key / 获取 Smart API Key

  1. Sign up / 注册: https://modelflare.dev/sign-up?utm_source=vscode&utm_medium=plugin&utm_campaign=integrations

  2. Console → API Keys → Create Smart API Key, and pick a routing strategy (Balanced / Stability first / Low price first). You can change the strategy on the key at any time.

    控制台 API Keys →「Create Smart API Key」,选择路由策略(均衡 / 稳定优先 / 低价优先),之后可随时在 Key 设置里修改。

Configure / 配置

  1. Open the chat model picker → Manage Models → Modelflare, or run Modelflare: Manage Modelflare API Key from the Command Palette.
  2. Paste your Smart API Key. It is stored in VS Code's secret storage, never in settings.
  3. Pick a Modelflare model in the chat model picker.
Setting Value
API key your Smart API Key (secret storage)
modelflare.baseUrl global → https://modelflare.dev/v1 (default) · china → https://origin.modelflare.dev/v1 · or a custom URL

Features / 功能

  • Text models available to your key, loaded from GET /v1/models?scope=authorized; new models appear without editing the key. Run Modelflare: Refresh Modelflare Models to reload.
  • Per-model context limits, output limits, tool calling, and vision capabilities from Modelflare's authenticated profile endpoint; the key is not sent to a third-party metadata service.
  • Image attachments for vision-capable models (PNG, JPEG, WEBP, and GIF) are forwarded through the OpenAI-compatible chat endpoint.
  • Streaming responses and tool calling for agent mode.
  • Routing across groups, fallback and the routing strategy are handled by the Smart API Key on the server.
  • Requests are billed by the group that served them; see the usage logs at https://modelflare.dev/usage-logs.

Troubleshooting / 常见问题

  • 401: the key is missing or invalid. Create a Smart API Key at https://modelflare.dev/keys.
  • model_not_found: a regular key only calls the models of its own group. A Smart API Key calls every model available to your account. If you already use a Smart API Key, that model is not available to your account right now.
  • 403 insufficient_user_quota: top up at https://modelflare.dev/billing.

Links

Docs: https://docs.modelflare.dev/ · Pricing: https://modelflare.dev/pricing

License

MIT © Havenbyte LLC

About

Use your Modelflare models in the VS Code chat model picker.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages