# NagaAI Documentation

## Docs

- [Overview](https://docs.naga.ac/get-started/overview.md): A unified AI platform for model access, API routing, and tool-compatible integrations.
- [Quickstart](https://docs.naga.ac/get-started/quickstart.md): Get your API key and make your first request to NagaAI using official SDKs.
- [Authentication](https://docs.naga.ac/get-started/authentication.md): Understand how to authenticate primary inference requests and administrative account operations.
- [Models](https://docs.naga.ac/get-started/models.md): Learn where to browse models in NagaAI, how free and paid access works, and how to choose a model for your task.
- [Choose an API](https://docs.naga.ac/get-started/choose-an-api.md): Decide whether to use Responses, Embeddings, Audio, Moderations, Images, or one of the compatibility layers.
- [Streaming](https://docs.naga.ac/build/streaming.md): Stream model output and events from Responses, Chat Completions, and Messages APIs.
- [Tool Calling](https://docs.naga.ac/build/tool-calling.md): Let models call your application-defined functions across the supported generation APIs.
- [Structured Outputs](https://docs.naga.ac/build/structured-outputs.md): Compare schema-shaped output patterns across the supported generation APIs.
- [Reasoning](https://docs.naga.ac/build/reasoning.md): Compare reasoning-related output across Responses, Chat Completions, and Messages.
- [Web Search](https://docs.naga.ac/build/web-search.md): Understand how search-capable behavior differs by model and API surface.
- [Multimodal Inputs](https://docs.naga.ac/build/multimodal-inputs.md): Compare how text, images, files, audio, and documents are represented across the supported APIs.
- [Tokens and Usage](https://docs.naga.ac/build/tokens-and-usage.md): Understand how models process data as tokens and how usage is categorized for billing.
- [Error Handling](https://docs.naga.ac/build/error-handling.md): Handle synchronous and streaming errors across NagaAI APIs.
- [Rate Limits](https://docs.naga.ac/build/rate-limits.md): Understanding rate limits and access tiers for NagaAI models.
- [How Billing Works](https://docs.naga.ac/build/billing.md): How credits, token pricing, and paid-model access work on NagaAI.
- [Production Checklist](https://docs.naga.ac/build/production-checklist.md): A practical checklist for shipping against NagaAI APIs reliably.
- [Responses API](https://docs.naga.ac/api/responses.md): Start here for new NagaAI LLM integrations.
- [Text Generation](https://docs.naga.ac/api/responses/text-generation.md): Generate text with the Responses API and understand the response item model.
- [Streaming](https://docs.naga.ac/api/responses/streaming.md): Stream semantic Responses API events and reconstruct the final result correctly.
- [Tool Calling](https://docs.naga.ac/api/responses/tool-calling.md): Call your own functions through the Responses API and understand tool items on the wire.
- [Structured Outputs](https://docs.naga.ac/api/responses/structured-outputs.md): Use schema-shaped output with the Responses API.
- [Reasoning](https://docs.naga.ac/api/responses/reasoning.md): Understand reasoning-related output in the Responses API.
- [Multimodal Inputs](https://docs.naga.ac/api/responses/multimodal-inputs.md): Send text, images, audio, and files through the Responses input model.
- [Web Search](https://docs.naga.ac/api/responses/web-search.md): Understand where search-capable requests fit into the Responses API workflow.
- [Conversation State](https://docs.naga.ac/api/responses/conversation-state.md): Model multi-turn context correctly when using the Responses API.
- [Tokens and Usage](https://docs.naga.ac/api/responses/tokens-and-usage.md): Understand how token usage, cached tokens, and reasoning tokens are reported in the Responses API.
- [Embeddings API](https://docs.naga.ac/api/embeddings.md): Generate vector embeddings for search, retrieval, and clustering workflows.
- [Batch Inputs](https://docs.naga.ac/api/embeddings/batch-inputs.md): Send multiple embedding inputs in one request and interpret the indexed results.
- [Output Formats](https://docs.naga.ac/api/embeddings/output-formats.md): Choose between JSON float vectors and base64-encoded embeddings.
- [Retrieval Patterns](https://docs.naga.ac/api/embeddings/retrieval-patterns.md): Use the Embeddings API in practical retrieval and ranking workflows.
- [Audio API](https://docs.naga.ac/api/audio.md): Convert text to speech and turn audio into text with transcription and translation endpoints.
- [Text to Speech](https://docs.naga.ac/api/audio/text-to-speech.md): Convert text into streamed audio bytes.
- [Speech to Text](https://docs.naga.ac/api/audio/speech-to-text.md): Upload audio and receive a text transcription.
- [Speech Translation](https://docs.naga.ac/api/audio/speech-translation.md): Upload audio and receive translated English text.
- [File Formats and Uploads](https://docs.naga.ac/api/audio/file-formats-and-uploads.md): Understand multipart uploads, validation, and common file issues for Audio API operations.
- [Moderations API](https://docs.naga.ac/api/moderations.md): Classify text and image inputs against moderation categories and scores.
- [Text Moderation](https://docs.naga.ac/api/moderations/text-moderation.md): Classify text inputs for moderation decisions.
- [Image Moderation](https://docs.naga.ac/api/moderations/image-moderation.md): Classify remote images with typed moderation inputs.
- [Mixed Inputs](https://docs.naga.ac/api/moderations/mixed-inputs.md): Moderate text and image content together in one request.
- [Images API](https://docs.naga.ac/api/images.md): Generate or edit images with direct image-focused endpoints.
- [Image Generation](https://docs.naga.ac/api/images/image-generation.md): Generate one or more images from a text prompt.
- [Image Edits](https://docs.naga.ac/api/images/image-edits.md): Edit one or more uploaded images with a prompt and optional mask.
- [Chat Completions API](https://docs.naga.ac/api/chat-completions.md): OpenAI-compatible chat endpoint for existing messages-based integrations.
- [Streaming](https://docs.naga.ac/api/chat-completions/streaming.md): Stream OpenAI-compatible chat completion chunks.
- [Tool Calling](https://docs.naga.ac/api/chat-completions/tool-calling.md): Use OpenAI-style tools and tool calls in the Chat Completions compatibility layer.
- [Reasoning](https://docs.naga.ac/api/chat-completions/reasoning.md): Understand reasoning-related controls and output on the Chat Completions compatibility surface.
- [Structured Outputs](https://docs.naga.ac/api/chat-completions/structured-outputs.md): Use JSON mode or schema-shaped output in the Chat Completions compatibility layer.
- [Multimodal Content](https://docs.naga.ac/api/chat-completions/multimodal-content.md): Send text, images, files, and audio through the Chat Completions compatibility layer.
- [Web Search](https://docs.naga.ac/api/chat-completions/web-search.md): Enable search on the Chat Completions compatibility surface with the real request field this endpoint supports.
- [Migration to Responses](https://docs.naga.ac/api/chat-completions/migration-to-responses.md): Move from Chat Completions to the recommended Responses API when you are ready.
- [Tokens and Usage](https://docs.naga.ac/api/chat-completions/tokens-and-usage.md): Usage tracking in the Chat Completions compatibility layer.
- [Messages API](https://docs.naga.ac/api/messages.md): Anthropic-compatible messages endpoint for Claude-style integrations and agent tooling.
- [Streaming](https://docs.naga.ac/api/messages/streaming.md): Stream Anthropic-style Messages API events.
- [Tool Use](https://docs.naga.ac/api/messages/tool-use.md): Use Anthropic-style tool_use and tool_result blocks.
- [Thinking Blocks](https://docs.naga.ac/api/messages/thinking-blocks.md): Understand thinking and reasoning-style content in the Messages compatibility layer.
- [Web Search](https://docs.naga.ac/api/messages/web-search.md): Enable Anthropic-style server web search on the Messages compatibility surface.
- [Documents and PDFs](https://docs.naga.ac/api/messages/documents-and-pdfs.md): Send document blocks and PDF sources through the Messages compatibility layer.
- [Migration to Responses](https://docs.naga.ac/api/messages/migration-to-responses.md): Move from Anthropic-style Messages contracts to the recommended Responses API when it makes sense.
- [Tokens and Usage](https://docs.naga.ac/api/messages/tokens-and-usage.md): Usage tracking in the Anthropic-compatible Messages API.
- [Account Management](https://docs.naga.ac/account/account-management.md): Manage operational account workflows with provisioning-key-protected endpoints.
- [API Keys](https://docs.naga.ac/account/api-keys.md): Create, list, update, and delete API keys with provisioning-key authentication.
- [Balance and Activity](https://docs.naga.ac/account/balance-and-activity.md): Inspect account balance, request volume, costs, top models, and per-key activity.
- [Privacy and Logging](https://docs.naga.ac/account/privacy-and-logging.md): Summary of how we handle prompts, outputs, and operational logs.
- [Playground](https://docs.naga.ac/product/playground.md)
- [Chat Interface](https://docs.naga.ac/product/chat-interface.md)
- [API Reference](https://docs.naga.ac/api-reference/overview.md): Exact endpoint contracts, request builders, auth requirements, and response schemas.
- [Create a response](https://docs.naga.ac/api-reference/responses/create-a-response.md): Creates a model response in the OpenAI Responses dialect and charges the account for the tokens it used. Requires an API key. `/v1/chat/completions` and `/v1/messages` serve the same models in the other two dialects.
- [Create a chat completion](https://docs.naga.ac/api-reference/chat-completions/create-a-chat-completion.md): Creates a model response in the OpenAI Chat Completions dialect and charges the account for the tokens it used. Requires an API key. `/v1/responses` and `/v1/messages` serve the same models in the other two dialects.
- [Create a message](https://docs.naga.ac/api-reference/messages/create-a-message.md): Creates a model response in the Anthropic Messages dialect and charges the account for the tokens it used. Requires an API key. `/v1/chat/completions` and `/v1/responses` serve the same models in the other two dialects.
- [List models](https://docs.naga.ac/api-reference/models/list-models.md): Returns the models NagaAI serves, whole and unpaged. Requires no key; presenting one narrows the catalog to what the account's balance can reach.
- [List startups](https://docs.naga.ac/api-reference/startups/list-startups.md): Returns the organizations whose models NagaAI serves. Requires no key, and presenting one changes nothing.
- [Create embeddings](https://docs.naga.ac/api-reference/embeddings/create-embeddings.md): Creates an embedding vector for the input and charges the account for the tokens it counted. Requires an API key.
- [Classify content](https://docs.naga.ac/api-reference/moderations/classify-content.md): Classifies text and images against a moderation model's categories and charges the account for the tokens it counted. Requires an API key.
- [Create speech](https://docs.naga.ac/api-reference/audio/create-speech.md): Converts text into spoken audio and charges the account for what it counted. Requires an API key.
- [Create a transcription](https://docs.naga.ac/api-reference/audio/create-a-transcription.md): Converts uploaded audio into text in the language that was spoken and charges the account for what it counted. Requires an API key. `/v1/audio/translations` answers in English instead.
- [Create a translation](https://docs.naga.ac/api-reference/audio/create-a-translation.md): Converts uploaded audio into English text and charges the account for what it counted. Requires an API key. `/v1/audio/transcriptions` answers in the language that was spoken.
- [Create an image](https://docs.naga.ac/api-reference/images/create-an-image.md): Creates images from a text prompt and charges the account for what it counted. Requires an API key. `/v1/images/edits` changes images that were uploaded instead.
- [Edit an image](https://docs.naga.ac/api-reference/images/edit-an-image.md): Edits uploaded images against a text prompt and charges the account for what it counted. Requires an API key. `/v1/images/generations` draws from a prompt alone.
- [Get the account balance](https://docs.naga.ac/api-reference/account/get-the-account-balance.md): Returns the account's credit balance. Requires a provisioning key.
- [Get account activity](https://docs.naga.ac/api-reference/account/get-account-activity.md): Returns the account's usage over a recent window, aggregated four ways. Requires a provisioning key.
- [List API keys](https://docs.naga.ac/api-reference/api-keys/list-api-keys.md): Returns every API key on the account, disabled and expired ones included. Requires a provisioning key.
- [Create an API key](https://docs.naga.ac/api-reference/api-keys/create-an-api-key.md): Creates an API key on the account and returns its secret this once. Requires a provisioning key.
- [Get an API key](https://docs.naga.ac/api-reference/api-keys/get-an-api-key.md): Returns one API key of the account, without its secret. Requires a provisioning key.
- [Update an API key](https://docs.naga.ac/api-reference/api-keys/update-an-api-key.md): Updates one API key of the account in place, changing only the fields sent. Requires a provisioning key.
- [Delete an API key](https://docs.naga.ac/api-reference/api-keys/delete-an-api-key.md): Deletes one API key of the account, immediately and past undoing. Requires a provisioning key.
- [Claude Code](https://docs.naga.ac/integrations/agents/claude-code.md): Use Claude Code with NagaAI to access multiple models through a single Anthropic-compatible endpoint.
- [Codex CLI](https://docs.naga.ac/integrations/agents/codex-cli.md): Use Codex CLI with NagaAI by adding a custom provider that points to NagaAI's OpenAI-compatible API.
- [Gemini CLI](https://docs.naga.ac/integrations/agents/gemini-cli.md): Use Gemini CLI with NagaAI by pointing an OpenRouter-compatible Gemini CLI fork to NagaAI’s OpenAI-compatible API.
- [Kilo Code](https://docs.naga.ac/integrations/agents/kilo-code.md): Use the Kilo Code VS Code extension with NagaAI via the OpenAI-compatible API.
- [OpenClaw](https://docs.naga.ac/integrations/agents/openclaw.md): Connect OpenClaw to NagaAI through the OpenAI-compatible API.
- [OpenCode](https://docs.naga.ac/integrations/agents/opencode.md): Use OpenCode with NagaAI by adding a custom provider to the OpenCode config file.
- [Roo Code](https://docs.naga.ac/integrations/agents/roo-code.md): Use the Roo Code VS Code extension with NagaAI via the OpenAI-compatible API.
- [Other Integrations](https://docs.naga.ac/integrations/agents/others.md): Connect NagaAI to any app or tool that supports OpenAI-compatible APIs (and more).

## OpenAPI Specs

- [naga-api](https://docs.naga.ac/openapi/naga-api.json)
- [openapi](https://docs.naga.ac/api-reference/openapi.json)