GET STARTED

Bring your existing app.

Connect an existing OpenAI-compatible application to Tokely.

Update three settings

Change your API base URL, API key and model ID. Keep using your existing OpenAI SDK for supported text requests. The key must be issued by Tokely, and the model must be enabled for the endpoint your app calls.

SettingTokely value
API base URLhttps://api.tokely.me/v1
API keyYour Tokely API key from the dashboard
ModelAn enabled model ID, such as gpt-5.4-mini for Chat Completions

Configure your SDK

Set these options where you create the client. Python uses base_url; JavaScript uses baseURL. TOKELY_API_KEY is an environment variable your code reads explicitly.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TOKELY_API_KEY"],
    base_url="https://api.tokely.me/v1",
)

Connect a tool with a custom endpoint

If your app supports a custom OpenAI-compatible provider, enter the base URL, Tokely key and supported model in its provider settings. An app that lets you change only the key may not support an alternative API server.

Use the base URL including /v1 when the setting asks for a base URL. If a field explicitly asks for a full Chat Completions endpoint, use https://api.tokely.me/v1/chat/completions. Avoid duplicating /v1 or /chat/completions.

Check the features your app uses

OpenAI compatibility covers the endpoints and parameters described here. It does not imply support for every API feature. Review input modalities, endpoint selection, tools, stored conversation behavior and model-specific streaming requirements before switching production traffic.

Your app usesWhat to do
Chat CompletionsChoose an enabled Chat Completions model.
ResponsesChoose an enabled Responses model; use store=false and send history yourself.
Function tools / structured JSONChoose a model with the corresponding capability.
Stored conversations / previous_response_idSend the relevant text history in each request.
Image / PDF inputUse inline base64 content parts with a compatible model; remote URLs and uploaded file IDs are not supported.
Image / video / audio generationUse the model-specific Media API endpoint, fields and billing unit; see the Media guide.
EmbeddingsPOST /v1/embeddings for the enabled OpenAI embedding models; see the Embeddings guide.
Reranking / hosted toolsThese contracts are not currently offered.

EXPLORE DOCUMENTATION

IntroductionConnect your app to AI models through one familiar API. This is your guide to building with Tokely.QuickstartMake your first Tokely request in three steps.API keysConnect securely with a key from your Tokely dashboard.ModelsChoose an available model and use its exact ID in your request.PlaygroundUse the Tokely Playground to test prompts before writing code.Use your existing appConnect an existing OpenAI-compatible application to Tokely.Chat CompletionsGenerate responses from text messages and supported inline images or PDFs.ResponsesUse stateless text and supported multimodal input with the Responses API.EmbeddingsTurn text into vectors for search, RAG, clustering and classification with the OpenAI-compatible /v1/embeddings endpoint.Claude Code and the Messages APIPoint Claude Code or the Anthropic SDK at Tokely. Use the native /v1/messages endpoint with streaming, tools and prompt caching.Images and PDFsSend inline images and PDFs to compatible models through Chat Completions or Responses.Images, video & audioGenerate media with your Tokely API key and account balance.Errors & limitsDiagnose failed requests and keep your integration within service limits.StreamingDisplay generated text as it arrives with server-sent events.Function callingLet a model request a function, then execute it in your application.Structured outputRequest JSON output or a defined schema from a compatible model.Usage & billingModel prices, account balance and output reservations.WebhooksTokely webhook events, HMAC signature verification, delivery retries and replay behavior.
Use Tab to browse results ESC to close