API Overview¶

stdapi.ai provides OpenAI and Anthropic compatible APIs backed by AWS Bedrock and AWS AI services. Any application that works with OpenAI or Anthropic works with stdapi.ai by simply changing the API endpoint.

Interactive Documentation¶

stdapi.ai provides multiple interfaces for exploring and testing the API—choose the one that fits your workflow:

Documentation Resources¶

Complete API Reference – In-depth guides for every endpoint with parameter details
OpenAPI Specification – Full machine-readable schema for integration and tooling

Live API Playground¶

When running the server, access these interactive interfaces (can be enabled via configuration options):

Interface	URL	Best For
Swagger UI	`http://localhost/docs`	Testing endpoints directly in your browser with live request/response examples
ReDoc	`http://localhost/redoc`	Reading and searching through clean, organized documentation
OpenAPI Schema	`http://localhost/openapi.json`	Generating client code or importing into API tools like Postman

Supported Endpoints¶

OpenAI-Compatible API¶

Category	Endpoint	Capability	Documentation
💬 Chat	`POST /v1/chat/completions`	Multi-modal conversations with text, images, video, documents	Chat Completions →
	`POST /v1/responses`	Stateless conversational AI with tool calling and streaming	Responses →
🎨 Images	`POST /v1/images/generations`	Text-to-image generation	Generations →
	`POST /v1/images/edits`	Image editing and transformations	Edits →
	`POST /v1/images/variations`	Generate image variations	Variations →
🔊 Audio	`POST /v1/audio/speech`	Text-to-speech synthesis	Text to Speech →
	`POST /v1/audio/transcriptions`	Speech-to-text transcription	Transcriptions →
	`POST /v1/audio/translations`	Speech-to-English translation	Translations →
🧠 Embeddings	`POST /v1/embeddings`	Vector embeddings for semantic search	Embeddings →
📋 Models	`GET /v1/models`	List available models	Models →
📁 Files	`POST/GET/DELETE /v1/files`	Upload, list, retrieve, download, delete files	Files →
	`POST /v1/uploads`	Multipart upload sessions for large files	Files →

stdapi.ai Native Extensions¶

Category	Endpoint	Capability	Documentation
🔍 Models	`GET /search_models`	Search models by capability: modality, route, MCP tool, region, streaming, legacy status	Search Models →

Anthropic-Compatible API¶

Category	Endpoint	Capability	Documentation
💬 Messages	`POST /anthropic/v1/messages`	Multi-modal conversations with text, images, video, documents	Messages →
	`POST /anthropic/v1/messages/count_tokens`	Count tokens without sending a message	Messages →
📋 Models	`GET /anthropic/v1/models`	List available models	Models →
	`GET /anthropic/v1/models/{model_id}`	Retrieve model details	Models →
📁 Files	`POST/GET/DELETE /anthropic/v1/files`	Upload, list, retrieve, download, delete files	Files →

MCP (Model Context Protocol)¶

When ENABLE_MCP_STREAMABLE_HTTP=true or ENABLE_MCP_SSE=true is configured, stdapi.ai exposes all its endpoints as MCP tools. The tool names follow the pattern provider_action.

JSON body support for file and audio tools

MCP tools send JSON bodies — they cannot construct multipart/form-data. All file upload, audio, and upload-part tools therefore accept the file or audio content as a base64 string, data URI (data:<mime>;base64,<data>), HTTPS URL, or S3 URI in the file / data field instead of a binary attachment. The full multipart upload workflow (openai_upload → openai_upload_part → openai_upload_complete) is fully MCP-compatible this way.

MCP Tool	Endpoint
OpenAI Tools
`openai_chat_completion`	`POST /v1/chat/completions`
`openai_response`	`POST /v1/responses`
`openai_image_generation`	`POST /v1/images/generations`
`openai_image_edit`	`POST /v1/images/edits`
`openai_image_variation`	`POST /v1/images/variations`
`openai_audio_speech`	`POST /v1/audio/speech`
`openai_audio_transcription`	`POST /v1/audio/transcriptions`
`openai_audio_translation`	`POST /v1/audio/translations`
`openai_embedding`	`POST /v1/embeddings`
`openai_model_list`	`GET /v1/models`
`openai_model_get`	`GET /v1/models/{model}`
`openai_file`	`POST /v1/files`
`openai_file_list`	`GET /v1/files`
`openai_files_get`	`GET /v1/files/{file_id}`
`openai_files_delete`	`DELETE /v1/files/{file_id}`
`openai_file_content`	`GET /v1/files/{file_id}/content`
`openai_upload`	`POST /v1/uploads`
`openai_upload_part`	`POST /v1/uploads/{upload_id}/parts`
`openai_upload_complete`	`POST /v1/uploads/{upload_id}/complete`
`openai_upload_cancel`	`POST /v1/uploads/{upload_id}/cancel`
Anthropic Tools
`anthropic_message`	`POST /anthropic/v1/messages`
`anthropic_message_count_tokens`	`POST /anthropic/v1/messages/count_tokens`
`anthropic_model_list`	`GET /anthropic/v1/models`
`anthropic_model_get`	`GET /anthropic/v1/models/{model_id}`
`anthropic_file`	`POST /anthropic/v1/files`
`anthropic_file_list`	`GET /anthropic/v1/files`
`anthropic_files_get`	`GET /anthropic/v1/files/{file_id}`
`anthropic_files_delete`	`DELETE /anthropic/v1/files/{file_id}`
`anthropic_file_content`	`GET /anthropic/v1/files/{file_id}/content`
Native Extension Tools
`search_models`	`GET /search_models`

Filtering MCP Tools

Use MCP_INCLUDE_TOOLS or MCP_EXCLUDE_TOOLS environment variables to control which tools are exposed. Always include search_models so agents can discover the right model ID dynamically. See Operations Configuration → for details.

Token Usage for Complex API Tools

anthropic_message, openai_chat_completion, and openai_response map to large, complex APIs that may use many tokens (prompt, completion, and tool definitions). Select these tools only if your workflow requires the full API capabilities.

Using stdapi.ai¶

stdapi.ai is a drop-in replacement for both OpenAI and Anthropic APIs. Any application that works with either provider—chatbots, coding assistants, automation tools, custom scripts—works with stdapi.ai by simply changing the API base URL.

Using the OpenAI-Compatible API¶

To connect your OpenAI application:

Replace the OpenAI API URL with your stdapi.ai deployment URL
Use the same authentication mechanism (Bearer token in the Authorization header)
Use AWS Bedrock model IDs (e.g., amazon.nova-micro-v1:0) or any configured model alias

That's it. Your application continues to work without any code changes—just point it to stdapi.ai instead of OpenAI.

Using the Anthropic-Compatible API¶

To connect your Anthropic application:

Replace the Anthropic API URL (https://api.anthropic.com) with your stdapi.ai deployment URL + /anthropic (e.g., https://your-endpoint.com/anthropic)
Use the same authentication mechanism (x-api-key header and anthropic-version header)
Use your preferred model name — official Anthropic names (e.g., claude-opus-4-6) are automatically resolved to Bedrock IDs, or use Bedrock model IDs directly

Your Anthropic SDK applications continue to work without any code changes—just point them to stdapi.ai instead of Anthropic.

Next Steps¶

Chat Completions — Conversational AI with multi-modal support
Images — Generation, edits, and variations
Audio — Text-to-speech, transcription, and translation
Embeddings — Vector embeddings for search and RAG
Models — List and discover available models
Search Models — Filter models by capability, modality, route, or MCP tool
Messages — Anthropic-compatible conversational AI with tool calling
Features — Full capabilities and AWS integrations
Getting Started — Deploy to AWS with Terraform
Use Cases — Integration examples with popular tools