file-docREST API Specs

API reference for Classic and Platform APIs with OpenAPI specs, SDKs, and developer tooling.

Amigo exposes two API surfaces, each auto-generated from its OpenAPI spec:

API
Built for
Auth
OpenAPI Spec

Text-based digital health

Organization-scoped JWT

Enterprise voice & healthcare

Workspace-scoped API key

Data-MCP

SQL query access to workspace data

API key + workspace header

N/A (MCP protocol)

message-botClassicchevron-rightphonePlatformchevron-rightclock-rotate-leftChange Logschevron-right
circle-info

Classic API covers conversations, users, tools, simulations, and data access. Organization-scoped with per-user JWT auth. Built for consumer-facing digital health products.

Platform API covers workspaces, agents, skills, services, integrations, phone numbers, operators, EHR sync, FHIR, CRM, and safety monitoring. Workspace-scoped with API key auth. Built for enterprise voice deployments and healthcare operations. All list endpoints support search filtering, delete operations check for dependencies, and rate limit headers appear on every response.

Data-MCP provides SQL query access to workspace data tables through the Model Context Protocol, with tools for querying, profiling, and exploring workspace tables (sql_query, describe_query, tables, table_schema, sample_data, table_detail, profile_column). Available as a Platform API service.

See the Developer Guidearrow-up-right for conceptual documentation on both APIs.

SDK Ecosystem

The Classic API is available through official SDKs. Platform API: Direct HTTP.

SDK Features

Both SDKs provide:

  • Automatic authentication: API key exchange for bearer tokens with proactive refresh

  • Retry with backoff: exponential backoff with jitter, Retry-After header support

  • NDJSON streaming: async generators for conversation create and interact endpoints

  • Type safety: full type definitions generated from the OpenAPI spec

  • Error hierarchy: typed error classes mapped to HTTP status codes

Multi-Provider LLM Support

Both APIs support multiple LLM providers with per-interaction model selection. Specify the provider and model at the interaction level. This avoids single-vendor lock-in and lets you optimize for cost, latency, and capability per task.

Ecosystem Tools

Last updated

Was this helpful?