GUIDES

Understand your usage.

Model prices, account balance and output reservations.

Prices per model

Image, video and audio models use the billing unit and fixed settings listed on their model pages, such as per image, second or task. Media requests may reserve an estimated cost before settlement; do not apply text token prices to media generation. Embeddings are billed per input token only, with no output charge.

Model pages publish input, output and, where available, cached input prices per million tokens in USD. Check the model’s current rates before calling it. Reference comparisons are labeled separately.

Charges use reported token usage and applicable rates. Reasoning can consume the output budget. Cache pricing applies when the model reports eligible cached input.

Balance and reservations

View your available USD balance in the dashboard. Requests use this balance across your API keys.

Before generation, the service reserves estimated input plus maximum output. It then settles actual usage and releases the unused reservation. Your balance and key budget must cover the reservation; a high output limit can cause a 402 even if the eventual answer would be short.

Fund your balance

Open Dashboard → Billing to add funds through the hosted crypto checkout. Current USD-equivalent deposits range from $10 to $10,000; the checkout shows available currencies and payment conditions. Funds become available after verified settlement, not merely after opening an invoice.

Card payments and enterprise invoicing are not currently offered.

Control account spending

Settings supports daily and monthly account budgets, with period boundaries in UTC. Reservations count against these limits across API keys and Playground. HTTP 402 with account_spend_limit means the account's spending limit was reached.

A key can also have a lifetime budget, model allowlist and IP restrictions. Key expiry is chosen when creating the key; create a replacement to change it.

Inspect usage

Read usage in a completed response. Cache and reasoning fields depend on the model and endpoint. Monetary rounding can affect very small requests.

X-Tokely-Pricing-Version identifies the active pricing version on successful generation responses. It does not replace published model rates.

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