# LLMTune Docs

## Docs

- [Agent API examples](https://docs.llmtune.io/agent/api-examples.md): Example requests and responses for the Agent.
- [Agent overview](https://docs.llmtune.io/agent/overview.md): What the Agent is and how it works.
- [Authentication](https://docs.llmtune.io/api/authentication.md): API key usage, headers, and security.
- [API endpoints](https://docs.llmtune.io/api/endpoints.md): Main REST endpoints by area.
- [API overview](https://docs.llmtune.io/api/overview.md): Base URL, response format, and general behavior.
- [Best practices](https://docs.llmtune.io/best-practices.md): Performance, tokens, timeouts, and production tips.
- [Balance and deductions](https://docs.llmtune.io/billing/balance-and-deductions.md): How balance works and what happens when it runs out.
- [Billing & usage](https://docs.llmtune.io/billing/usage.md): How usage is calculated and tracked.
- [Datasets](https://docs.llmtune.io/core-concepts/datasets.md)
- [Model Configuration](https://docs.llmtune.io/core-concepts/model-configuration.md)
- [Usage Metering](https://docs.llmtune.io/core-concepts/usage-metering.md)
- [Workspaces](https://docs.llmtune.io/core-concepts/workspaces.md)
- [Errors & status codes](https://docs.llmtune.io/errors/status-codes.md): Unified error format and HTTP status codes.
- [FAQ](https://docs.llmtune.io/faq.md)
- [Dataset format](https://docs.llmtune.io/fine-tuning/dataset-format.md): Supported formats and structure for fine-tuning.
- [Fine-tuning limitations](https://docs.llmtune.io/fine-tuning/limitations.md): Current limits and constraints.
- [Fine-tuning overview](https://docs.llmtune.io/fine-tuning/overview.md): How fine-tuning works on the platform.
- [Fine-tuning workflow](https://docs.llmtune.io/fine-tuning/workflow.md): Steps from dataset to deployed model.
- [Getting started](https://docs.llmtune.io/getting-started.md): Account setup, API keys, and your first request.
- [Deployment Guide](https://docs.llmtune.io/guides/deployment.md)
- [Evaluate](https://docs.llmtune.io/guides/evaluate.md)
- [Fine-Tuning Guide](https://docs.llmtune.io/guides/fine-tuning.md)
- [Inference API Guide](https://docs.llmtune.io/guides/inference-api.md)
- [Webhooks](https://docs.llmtune.io/guides/webhooks.md)
- [LLMTune Overview](https://docs.llmtune.io/index.md): Orient yourself within the LLMTune platform and documentation.
- [Chat completions](https://docs.llmtune.io/inference/chat-completions.md): Request format, parameters, and response for chat.
- [Errors and rate limits](https://docs.llmtune.io/inference/errors-and-limits.md): Rate limits and error handling for inference.
- [Inference overview](https://docs.llmtune.io/inference/overview.md): Chat completions, standard completions, and how inference works.
- [Streaming](https://docs.llmtune.io/inference/streaming.md): How to request and consume streaming responses.
- [Introduction](https://docs.llmtune.io/introduction.md): What the platform is and what it can do.
- [Quickstart](https://docs.llmtune.io/quickstart.md)
- [Roadmap](https://docs.llmtune.io/roadmap.md)

## OpenAPI Specs

- [openapi](https://docs.llmtune.io/api-reference/openapi.json)

## Optional

- [Main site](https://llmtune.io)
- [Dashboard](https://llmtune.io/login)