UplinkSwitch

    • One API key for Claude,
    GPT and Gemini.

    UplinkSwitch sits between your code and the AI providers. Keep the SDK you already use, change the URL and the key, and get team keys, spending limits and a log of every request on top.

    See how it works Request a key

    https://api.uplinkswitch.com/v1

    "Your"YourteamteamalreadyalreadyusesusesthetheOpenAI,OpenAI,AnthropicAnthropicororGeminiGeminiSDK.SDK.KeepKeepit.it.PointPointititatatoneoneURL,URL,handhandoutoutoneonekeykeyperperperson,person,andandseeseeeveryeverycallcallininoneoneplace."place."

    Works with the official OpenAI, Anthropic and Gemini SDKs, and with Claude Code. You change two settings: the URL and the API key.

    Claude
    OpenAI
    Gemini

    Everything your team needs around the model APIs. A key for each person, limits you control, and a clear record of every request. The models still come straight from OpenAI, Anthropic and Google.

    Fast from anywhere. Your request enters UplinkSwitch at the Cloudflare location closest to you, gets checked against your key and limits, and goes straight on to the provider.

    Every model in one list. Ask for the model list and you get everything your key can use: Claude, GPT, Gemini, and open models as we add them. Each entry says who runs it.

    "Your key is fine, but Anthropic isn't responding right now. Nothing was charged."

    What an error looks like

    Every error says what went wrong. You never pay for a request that didn't reach the model.

    See what every call cost. Each request is logged with the model, the provider that ran it, the token counts the provider reported, and the charge. Figures here are an example.

    Nothing hidden in the response. Four headers on every reply tell you the request id, which provider ran it, how it was billed, and where the token counts came from.

    Simple pricing. Load a prepaid balance and pay per request. With your own provider keys, each request costs $0.001 on top of what the provider charges you. Open models we host are priced per million tokens. Top-ups are not refundable. The chart is sample data.

    $0.001

    Per request, using your own provider key

    $10

    Minimum top-up

    3

    Providers behind one URL

    60 s

    Until a revoked key stops working

    Works with the providers you already pay. Pick a model. UplinkSwitch sends the call to the right provider and logs it the same way every time.

    ANAnthropic · your account

    Claude

    Use the Anthropic SDK or Claude Code exactly as you do today. Calls go to Anthropic on your own Anthropic account and stream back unchanged.

    OAOpenAI · your account

    GPT

    Chat, responses and embeddings through the OpenAI SDK, on your own OpenAI account. One UplinkSwitch key per teammate instead of one shared secret.

    GOGoogle · your account

    Gemini

    The Gemini SDK, pointed at one URL. Calls go to Google on your own Google account, including streaming.

    VLHosted by UplinkSwitch

    Open models

    Llama and other open models on servers we run, priced per million tokens. Coming online as we add capacity.

    Common questions. Something else? Contact us.

    Get your key.

    Load $10, point your SDK at api.uplinkswitch.com, and your first request shows up in the log a second later.

    Request a key