# TokModel

> Documentation for TokModel — the unified LLM API gateway for 30+ AI model providers.

## Docs

- [Manage your TokModel API keys: create, rotate, revoke](https://docs.tokmodel.com/account/api-keys.md): Learn how to create, name, use, rotate, and revoke TokModel API keys to authenticate your application and keep credentials secure.
- [TokModel console: manage API keys, credits, and usage](https://docs.tokmodel.com/account/console.md): The TokModel console is your central hub for managing API keys, monitoring usage, checking your credit balance, and exploring available models.
- [Top up credits on your TokModel account: billing guide](https://docs.tokmodel.com/account/top-up.md): TokModel uses a credit-based billing system. Learn how to top up your balance, understand credit consumption, and avoid API failures from an empty account.
- [Audio speech, transcription, and translation](https://docs.tokmodel.com/api-reference/audio.md): Synthesize speech from a text string, transcribe uploaded audio files to text, or translate audio into English using TokModel's three audio endpoints.
- [POST /v1/chat/completions](https://docs.tokmodel.com/api-reference/chat-completions.md): OpenAI-compatible chat completions endpoint. Send a list of messages and receive a model-generated reply, with optional streaming support.
- [POST /v1/embeddings — Text Embeddings](https://docs.tokmodel.com/api-reference/embeddings.md): Generate vector embeddings for one or more text inputs. Use embeddings for semantic search, clustering, classification, and retrieval-augmented generation.
- [Image generation, editing, and variations](https://docs.tokmodel.com/api-reference/images.md): Generate images from text prompts, edit existing images with a mask, or create variations of an image using TokModel's three image endpoints.
- [POST /v1/messages — Anthropic Messages API](https://docs.tokmodel.com/api-reference/messages.md): Anthropic-compatible messages endpoint. Send requests using the Anthropic API format and authenticate with your TokModel key instead of an Anthropic key.
- [GET /v1beta/models — List Available Models](https://docs.tokmodel.com/api-reference/models.md): Retrieve the complete list of models available on TokModel, including each model's ID, owning provider, and creation timestamp for routing requests.
- [TokModel API reference overview](https://docs.tokmodel.com/api-reference/overview.md): Complete reference for the TokModel API. Covers the base URL, authentication header, content type, all available endpoints, and standard HTTP error codes.
- [POST /v1/rerank — Document Reranking](https://docs.tokmodel.com/api-reference/rerank.md): Rerank a list of documents by relevance to a query. Returns scored results sorted from most to least relevant for use in RAG and search pipelines.
- [POST /v1/responses — OpenAI Responses API](https://docs.tokmodel.com/api-reference/responses.md): OpenAI Responses API format endpoint. Submit a prompt and receive a structured response, with a compact variant that returns only the plain output text.
- [How to authenticate requests with the TokModel API](https://docs.tokmodel.com/authentication.md): Learn how to authenticate API requests using your TokModel API key, and understand the error responses returned for invalid or missing credentials.
- [Credits and billing on TokModel](https://docs.tokmodel.com/concepts/credits.md): TokModel uses a prepaid credit system. Credits are deducted per request based on token usage and the price multiplier for the model you call.
- [How the TokModel API gateway works](https://docs.tokmodel.com/concepts/gateway.md): TokModel is a single API endpoint that routes your requests to 30+ AI model providers, so you never have to manage multiple provider keys or SDKs.
- [Models and providers available on TokModel](https://docs.tokmodel.com/concepts/models.md): TokModel gives you access to models from 30+ AI providers through a single endpoint, using a consistent provider-prefixed model ID format.
- [Text-to-speech, transcription, and audio translation](https://docs.tokmodel.com/guides/audio.md): Synthesize speech from text, transcribe audio files to text, and translate spoken audio into English using TokModel's audio endpoints.
- [Send chat completions using TokModel's unified LLM API](https://docs.tokmodel.com/guides/chat-completions.md): Use TokModel's OpenAI-compatible chat endpoint to generate text, hold conversations, and stream responses from 30+ model providers.
- [Generate text embeddings using TokModel's gateway API](https://docs.tokmodel.com/guides/embeddings.md): Convert text into dense vector embeddings via TokModel's /v1/embeddings endpoint — compatible with any OpenAI embeddings client.
- [Generate, edit, and vary images via TokModel's API](https://docs.tokmodel.com/guides/image-generation.md): Create new images from text prompts, edit existing images with a mask, or generate stylistic variations using TokModel's image endpoints.
- [Rerank documents for relevance scoring with TokModel](https://docs.tokmodel.com/guides/reranking.md): Use TokModel's /v1/rerank endpoint to sort a list of documents by relevance to a query — ideal for improving RAG retrieval precision.
- [TokModel: A Unified LLM API Gateway for Developers](https://docs.tokmodel.com/introduction.md): Learn what TokModel is, how the OpenAI-compatible gateway works, and which endpoint types and providers are available for your applications.
- [Quickstart: Get started with the TokModel API fast](https://docs.tokmodel.com/quickstart.md): Create a TokModel account, generate your API key, and send your first chat completions request to any supported model using curl, Python, or Node.js.

## Optional

- [Console](https://tokmodel.com/console)