GET STARTED

Try a model. Start a conversation.

Use the Tokely Playground to test prompts before writing code.

Start chatting

Open the Playground and sign in to your Tokely account. Choose an available text or media model, fill in its required inputs and send the request. Generation uses your account balance; you do not need to paste an API key into the Playground.

Use the model picker to search by model or provider. It lists enabled models. Text uses input/output token prices; media uses the billing unit and supported variant on its model page.

Adjust your request

Chat settings let you set maximum output tokens, temperature where supported, and system instructions. Settings apply to your next request. Reasoning tokens count toward the output budget.

Stop generation with the square button. Regenerate or retry makes a new API request and uses your balance. The selected model determines whether the request uses Chat Completions or Responses and whether streaming is available.

Keep your conversations

Use the sidebar to start a new chat, search, rename, reopen or delete a conversation. Signed-in chats are saved to your account and load when you open Playground on another device. Existing local chats are imported without replacing chats already saved in your account.

Conversation history is sent with each text request to provide context. Its input tokens contribute to usage. A conversation that reaches the request limits needs a new chat.

Generate images, video or audio

Choose an enabled media model. Its settings show the required prompt, reference URLs, voice or other fields and the supported output variant. Fill required fields before submitting.

Accepted background tasks continue independently of browser progress checks. Stopping checks does not cancel a paid task. Reopen its existing result rather than automatically submitting it again. Generated results are kept for 30 days; save outputs you need to keep.

Take the prompt to your app

Use View API request to copy a cURL example with the current model, conversation and settings. Create your own API key in the dashboard and set TOKELY_API_KEY before running it. Copy response and code block controls help you reuse generated text.

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