GET STARTED

Find the right model.

Choose an available model and use its exact ID in your request.

Explore the catalog

Browse Models to compare providers, capabilities, context limits and token prices. A catalog entry alone does not mean the model can be called. Check its availability and supported endpoint on the model page.

Some models require streaming. Some support Responses only. Structured output and function calling depend on the model.

GET /v1/models

This authenticated endpoint lists enabled public model IDs. Use an exact ID from the list in the model field. The response does not include full capability or pricing metadata. Embedding models appear in this list but not in the public model catalog; their IDs and prices are in the Embeddings guide.

curl https://api.tokely.me/v1/models \
  -H "Authorization: Bearer $TOKELY_API_KEY"

Choose a routing mode

Account Settings offers Balanced, Lowest cost, Fastest, Most reliable and Fixed. For a new API request, X-Tokely-Routing can select balanced, lowest-cost, fastest, most-reliable or fixed.

Published prices apply to the normal route. When a selected or fallback supplier costs more, the charge rises to cover its verified procurement tariff without requiring an additional margin. The engine reserves the selected route charge before starting work; insufficient balance or an unknown supplier price prevents submission. Eligible native fallback routes are ordered by comparable estimated route cost. These estimates are not guaranteed supplier charges. Adaptive selection needs eligible routes and sufficient quotes or measurements. When those are unavailable, the receipt explains a fallback to Balanced. Lowest cost uses a normalized token mix; it is not a guarantee for every workload. A single-route model has no route fallback.

Context and output

The service accepts an explicit output limit up to the lower of the model’s published limit and 262,144 tokens. Models without an established output limit use a 4,096-token service cap.

The default output budget is 256 tokens, including reasoning. Increase it for longer answers and reasoning models, and ensure your balance covers the reservation.

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