What you can do with the API
Run agents programmatically
Launch new executions, pause or resume them, complete runs, and trigger automated evaluations.
Power conversational assistants
Send messages to assistants, retrieve chat histories and integrate them directly inside your product.
Monitor quality with evaluations
Score outputs, audit behaviour and receive structured feedback using Devic’s evaluation engine.
FinOps and cost visibility
Retrieve daily, monthly and aggregated cost data for each agent.
Docs as an API
Access your workspace documentation as rendered HTML or raw markdown.
Health checks
Verify API availability using a dedicated health endpoint.
API surface at a glance
The Devic API is divided into the following groups:Agents
- Create and list agent threads
- Pause, resume or complete executions
- Trigger evaluations
- Retrieve evaluation results
- Retrieve daily, monthly and summary costs
Assistants
- List available assistants
- Send messages
- Retrieve chat histories
- Filter conversations across assistants
Documentation
- List available docs
- Retrieve rendered HTML or markdown
Health
- Basic availability checks
View OpenAPI specification
Download the OpenAPI specification used to generate this API reference.
Environments and base URLs
Devic offers separate environments for development and production.Production
https://api.devic.aiStaging
https://staging-api.devic.ai Example full endpoint: GET https://api.devic.ai/v1/agents/{agentId}/threadsAuthentication
All Devic API requests require a Bearer token. Include your token in every request using theAuthorization header:
Header format:
Authorization: Bearer YOUR_API_TOKEN
Example request:
GET https://api.devic.ai/v1/agents/{agentId}/threads
Authorization: Bearer YOUR_API_TOKEN
Content-Type: application/json
Invalid or missing tokens return 401 Unauthorized.
Typical workflows
1. Running an agent
- Create a thread POST /v1/agents//threads
- Monitor or control the execution GET /v1/agents/threads/ POST /v1/agents/threads//pause POST /v1/agents/threads//resume POST /v1/agents/threads//complete
- Trigger or fetch evaluations POST /v1/agents/threads//evaluate GET /v1/agents/threads//evaluations
- Inspect costs GET /v1/agents/agents//costs/daily GET /v1/agents/agents//costs/monthly GET /v1/agents/agents//costs/summary
Start with agents
Create your first execution thread programmatically.
2. Conversational assistants
- List assistants GET /v1/assistants
- Send messages POST /v1/assistants//messages
- Retrieve chat history GET /v1/assistants//chats/ GET /v1/assistants//chats POST /v1/assistants/chats
Start with assistants
Learn how to send your first message to an assistant.
Error handling
Most endpoints return structured error objects. Common status codes:- 400 — Invalid input
- 401 — Missing or invalid token
- 404 — Resource not found
- 429 — Rate limit exceeded
- 500 — Internal server error