openrout.ing — API Documentation

Overview

openrout.ing provides two API endpoints, both unlocked by a single API key:

raw.openrout.ing/v1 — Direct OpenAI-compatible completions via Featherless AI. Pure model access with zero orchestration overhead. 22,250+ open-source models including Qwen3-8B, Qwen2.5-3B-Instruct, Qwen3-Embedding-0.6B, DeepSeek-V4-Pro, DeepSeek-V4-Flash, DeepSeek-V3.2, and more. Features zero 429 rate limiting (unlimited Redis-backed queue), model coalition fallback (41 model mappings, 3 retries per model), per-client concurrency slots (tier-based: 4 to unlimited), streaming (SSE) and non-streaming inference, token usage tracking per client per day per model, and embeddings (Qwen3-Embedding-0.6B, 1024 dimensions). Response headers include X-Tier, X-Model-Used, X-Coalition, X-Queue-Wait, and X-Request-ID. Use this when you need raw inference speed and direct model access.
api.openrout.ing/v1 — Intelligent inference with a full agentic runtime. Every request runs through a context enrichment pipeline that adds relevant memories and knowledge before LLM inference (X-Enrichment-Ms, X-Enriched headers). 904 pre-built specialized AI agents across medical, financial, security, architecture, creative, and executive domains. Tiered memory system (core/recall/archival) with temporal search and consolidation. Knowledge graphs with entity-relation mapping and auto-build from text. Workflow engine with chaining, LLM-powered execution, and custom workflow creation. Multi-agent collaboration with task delegation, inter-team delegation, and A2A protocol. Skills marketplace with publish/install/rate. MCP server integration. Guardrails with rule-based content safety. Event sourcing with append-only log and replay. Episodic memory with entity tracking and temporal facts. All included free with every plan.

Both endpoints share the same authentication (Bearer token API keys), the same model catalog (22,250+ open-source models via Featherless AI), and the same billing account (Square integration, 6 tiers from starter to enterprise). Switch between them by changing only the base URL. The backend at openrout.ing also provides 347 API endpoints across v1, v2, v4, and v5 APIs covering auth, billing, agents, knowledge bases, MCP servers, workflows, skills, tools, A2A protocol, durable agents, batch processing, feature flags, WASM tools, persistent workflows, memory tiers, facts, events, pipelines, plugins, templates, tools, tree of thought, knowledge graph, hubs, guardrails, scheduler, observability, and rate limits.

Base URLs:

https://raw.openrout.ing — Raw Inference API (OpenAI-compatible, direct model access)
https://api.openrout.ing — Intelligence API (enriched inference, 904 agents, memory, workflows)
https://openrout.ing — Backend API (auth, billing, management, 347 endpoints)

Quick Start

Raw inference

# Set your API key
export OPENROUTING_API_KEY="sk-or-..."

# List available models
curl https://raw.openrout.ing/v1/models \
  -H "Authorization: Bearer $OPENROUTING_API_KEY"

# Chat completion
curl https://raw.openrout.ing/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Intelligent inference

# Create an agent
curl -X POST https://api.openrout.ing/v1/agents \
  -H "Authorization: Bearer $OPENROUTING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Assistant",
    "model": "Qwen/Qwen3-235B-A22B",
    "system_prompt": "You are a helpful assistant."
  }'

# Chat with the agent (autonomous tool-calling loop)
curl -X POST https://api.openrout.ing/v1/agents/{agent_id}/chat \
  -H "Authorization: Bearer $OPENROUTING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "What is the weather in London?"
  }'

Python SDK

# Raw inference — drop-in OpenAI replacement
from openai import OpenAI

client = OpenAI(
    base_url="https://raw.openrout.ing/v1",
    api_key="sk-or-..."
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Authentication

All requests require an Authorization: Bearer sk-or-... header. API keys are created in the dashboard at openrout.ing/login. Keys work across both endpoints — raw and intelligent.

Authorization: Bearer sk-or-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Error Codes

Code	HTTP	Description
missing_key	401	Authorization header not provided
invalid_key	401	API key not found or revoked
rate_limit	429	Concurrency limit exceeded for your tier
model_not_found	404	Requested model ID does not exist
insufficient_quota	403	Token allowance exhausted for billing period
internal_error	500	Server error — retry after a few seconds

Raw Inference API — raw.openrout.ing

The raw API provides direct, high-speed model access with zero orchestration. It is fully OpenAI-compatible — drop-in replacement for the OpenAI SDK by changing only the base URL. Every request goes straight to the model and back. No containers, no memory, no tool loops. Maximum speed, minimum latency.

POST /v1/chat/completions

Create a chat completion. Supports streaming, tool calling, JSON mode, structured output, and all standard OpenAI parameters.

POSThttps://raw.openrout.ing/v1/chat/completions

OpenAI-compatible chat completions endpoint

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model ID (e.g. `deepseek-ai/DeepSeek-V4-Pro`)
messages	array	Yes	Array of message objects with role and content
max_tokens	integer	No	Maximum tokens to generate
temperature	number	No	Sampling temperature (0-2). Default: 1
top_p	number	No	Nucleus sampling threshold. Default: 1
stream	boolean	No	Stream tokens via SSE. Default: false
tools	array	No	Function/tool definitions for tool calling
tool_choice	string/object	No	`auto`, `none`, `required`, or specific tool
response_format	object	No	`{"type":"json_object"}` or JSON schema for structured output
seed	integer	No	Deterministic sampling seed
logprobs	boolean	No	Return log probabilities. Default: false

Example

curl https://raw.openrout.ing/v1/chat/completions \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-235B-A22B",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Explain quantum entanglement in 50 words"}
    ],
    "max_tokens": 200,
    "temperature": 0.7,
    "stream": false
  }'

GET /v1/models

List all available models. Returns model ID, context length, features, and model class.

GEThttps://raw.openrout.ing/v1/models

List all 22,298+ models available on the platform

curl https://raw.openrout.ing/v1/models \
  -H "Authorization: Bearer sk-or-..."

# Response (truncated)
{
  "data": [
    {
      "id": "deepseek-ai/DeepSeek-V4-Pro",
      "context_length": 262144,
      "model_class": "deepseek4-1.6t",
      "concurrency_cost": 4,
      "features": {"tool_use": true},
      "owned_by": "Feather",
      "available_on_current_plan": true
    }
  ]
}

POST /v1/embeddings

POSThttps://raw.openrout.ing/v1/embeddings

Generate embeddings for text input

curl https://raw.openrout.ing/v1/embeddings \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-Embedding-8B",
    "input": "Hello world"
  }'

Model Parameters

Each model object in /v1/models includes:

id — Model identifier used in API calls
context_length — Maximum context window in tokens
concurrency_cost — Number of concurrency slots consumed (larger models cost more)
features.tool_use — Whether the model supports parallel tool calling
model_class — Architecture family (e.g. deepseek4-1.6t, qwen3-235b, glm51-754b)
available_on_current_plan — Whether your tier can access this model

Intelligent Inference API — api.openrout.ing

The intelligent API wraps every request in a full agentic runtime. When you send a message, the platform does not just generate text — it enters an autonomous loop: the model plans, calls tools, reads results, reasons about what it found, and iterates until the task is complete. All of this happens inside a containerised environment with persistent memory, knowledge retrieval, guardrails, and observability.

Every intelligent endpoint is included free with your plan. There are no additional charges for agents, memory, knowledge bases, or workflows — they all consume tokens from your plan allowance.

Agents

An agent is a persistent entity with its own system prompt, model, tools, knowledge bases, and memory. Create it once, then chat with it repeatedly across sessions. The agent remembers previous conversations via warm memory.

POST/v1/agents

Create a new agent

curl -X POST https://api.openrout.ing/v1/agents \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Research Assistant",
    "model": "Qwen/Qwen3-235B-A22B",
    "system_prompt": "You are a research assistant. Use tools to find information. Always cite sources.",
    "knowledge_base_ids": ["kb_abc123"],
    "mcp_server_ids": ["mcp_def456"],
    "guardrail_ids": ["gr_no_pii"]
  }'

# Response
{
  "id": "agent_x9f2k",
  "name": "Research Assistant",
  "model": "Qwen/Qwen3-235B-A22B",
  "created_at": "2026-06-16T06:00:00Z"
}

GET/v1/agents

List all agents

GET/v1/agents/{agent_id}

Get agent details

DELETE/v1/agents/{agent_id}

Delete an agent

Agent Chat

Send a message to an agent. The agent enters an autonomous loop — calling tools, reading outputs, reasoning — until the task is complete. Each chat request may trigger multiple model calls internally. The response includes the final answer plus a trace of all tool calls made.

POST/v1/agents/{agent_id}/chat

Send a message to an agent (autonomous multi-step execution)

curl -X POST https://api.openrout.ing/v1/agents/agent_x9f2k/chat \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Find the latest revenue figures for Tesla and compare with analyst estimates",
    "stream": false
  }'

# Response
{
  "agent_id": "agent_x9f2k",
  "response": "Based on the search results, Tesla Q1 2026 revenue was...",
  "tool_calls": [
    {"tool": "web_search", "input": {"query": "Tesla Q1 2026 revenue"}, "output": "..."},
    {"tool": "web_search", "input": {"query": "Tesla Q1 2026 analyst estimates"}, "output": "..."}
  ],
  "tokens_used": 3847,
  "steps": 3
}

Supports streaming via "stream": true which returns SSE events for each tool call and reasoning step.

Memory

Three-tier memory system that persists across sessions. The agent automatically manages what goes where — no manual curation required.

Hot memory — The active conversation window. Everything the agent is currently working on stays in context.
Warm memory — Auto-extracted facts, entities, and relationships persisted across sessions. The agent remembers your preferences, past decisions, and project context without re-explanation.
Cold memory — Archived knowledge retrieved on demand via semantic search from vector stores.

GET/v1/agents/{agent_id}/memory

List all memories for an agent

POST/v1/agents/{agent_id}/memory

Add a memory manually

POST/v1/agents/{agent_id}/memory/query

Semantic search across agent memories

GET/v1/agents/{agent_id}/memory/stats

Memory usage statistics per tier

DELETE/v1/agents/{agent_id}/memory/{memory_id}

Delete a specific memory

Knowledge Bases

Upload documents (PDF, markdown, code, databases, URLs) and the platform auto-chunks, embeds, and indexes everything. At inference time, agents retrieve semantically relevant context and inject it into their prompt. Hybrid search combines dense vector similarity with keyword matching. Unlimited knowledge bases per account.

POST/v1/knowledge-bases

Create a knowledge base

GET/v1/knowledge-bases

List all knowledge bases

POST/v1/knowledge-bases/{kb_id}/documents

Upload documents to a knowledge base

POST/v1/knowledge-bases/{kb_id}/query

Semantic search within a knowledge base

DELETE/v1/knowledge-bases/{kb_id}

Delete a knowledge base

Knowledge Graph

As conversations happen, the platform automatically extracts entities and relationships — people, organisations, concepts, events — and constructs a knowledge graph. Agents query this graph to find connected information that pure vector search would miss. The graph grows and refines itself over time.

POST/v5/kg/entities

List or search entities in the knowledge graph

POST/v5/kg/relations

List or search relations between entities

POST/v5/kg/search

Combined entity + relation search

POST/v5/kg/auto-build

Trigger automatic graph construction from agent conversations

GET/v5/kg/stats

Graph statistics (entity count, relation count, etc.)

MCP Servers

Connect to external tools and data sources via the Model Context Protocol. 9,973 pre-built MCP servers are available — file systems, SQL databases, REST APIs, browsers, code execution sandboxes, cloud services, and more. Your agent calls them as tools during execution.

GET/v1/mcp-servers

List available MCP servers

POST/v1/mcp-servers

GET/v1/mcp-servers/{mcp_id}

Get MCP server details and available tools

DELETE/v1/mcp-servers/{mcp_id}

Remove an MCP server

Workflows

Define DAG (directed acyclic graph) pipelines that chain agents together. Each node is an agent with its own tools, memory, and knowledge. Workflows support branching on conditions, parallel execution, and error recovery with retry and fallback. Trigger on schedule (cron) or on events (webhook, message queue).

POST/v1/workflows

Create a workflow

GET/v1/workflows

List all workflows

GET/v1/workflows/{workflow_id}

Get workflow definition

POST/v1/workflows/{workflow_id}/run

Execute a workflow

GET/v1/workflows/{workflow_id}/runs

List workflow execution history

curl -X POST https://api.openrout.ing/v1/workflows \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Research Pipeline",
    "nodes": [
      {"id": "research", "agent_id": "agent_research"},
      {"id": "validate", "agent_id": "agent_validator"},
      {"id": "write", "agent_id": "agent_writer"}
    ],
    "edges": [
      {"from": "research", "to": "validate"},
      {"from": "validate", "to": "write", "condition": "passed"},
      {"from": "validate", "to": "research", "condition": "failed"}
    ],
    "schedule": "0 9 * * 1"
  }'

Skills

Installable prompt-and-tool templates that give agents new capabilities instantly. A skill packages a system prompt, tool definitions, MCP connections, and example interactions into one unit. Browse 6,000+ community skills or build your own.

GET/v1/skills

List available skills

GET/v1/skills/{skill_id}

Get skill details

Guardrails

Seven layers of safety and compliance applied at inference time inside the runtime:

Input filtering — Block prompt injections, jailbreaks, and malicious instructions
Output validation — Scan completions for policy violations
PII redaction — Detect and mask personal data
Topic restriction — Confine agents to approved subject areas
Toxicity detection — Filter harmful content
Instruction-injection defence — Prevent tool outputs from hijacking agent behaviour
Custom rules — Define your own allow/deny patterns per agent

POST/v5/guardrails/check

Run guardrail checks on text

GET/v5/guardrails/rules

List all guardrail rules

POST/v5/guardrails/rules

Create a custom guardrail rule

GET/v5/guardrails/logs

View guardrail audit logs

Multi-Agent

Swarm orchestration with supervisor pattern. A coordinator agent receives the request, breaks it into subtasks, and delegates to specialist agents. Each specialist has its own system prompt, tools, memory, and knowledge. Results merge back into a single coherent response.

POST/v5/agents/spawn

Spawn a sub-agent from a parent agent

GET/v5/agents/spawns

List active sub-agents

GET/v5/agents/spawns/{spawn_id}

Get sub-agent status and results

Scheduler

Cron and event-driven triggers. Schedule an agent to run on a recurring basis, or trigger a workflow when a webhook fires. No external cron service needed.

POST/v5/schedule

Create a scheduled task (cron or event-driven)

GET/v5/schedule

List all scheduled tasks

DELETE/v5/schedule/{name}

Cancel a scheduled task

Observability

Full execution traces for every request. Eight integrated tools:

Distributed traces — Follow a request across agents, tools, and MCP servers
Metrics — Latency, token usage, tool call counts
Logs — Structured logging for every runtime event
Error tracking — Automatic capture, grouping, and alerting
Latency profiling — Identify bottlenecks in agent loops
Token accounting — Per-agent, per-tool, per-request breakdown
Cost attribution — Map token spend back to agents and workflows
Audit logs — Immutable record of every action for compliance

GET/v5/observability/metrics

System and request metrics

GET/v5/observability/errors

Error tracking and grouping

GET/v5/observability/usage

Token usage and cost attribution

GET/v5/observability/snapshot

Current system state snapshot

All Endpoints (301)

Complete list of all 301 API endpoints. Click "Try it" to test any endpoint live. Download the Postman Collection.

health (1)

GET/health

Health

metrics (1)

GET/metrics

Metrics

v1/admin (1)

POST/v1/admin/reset-tokens

Admin Reset Tokens

v1/agents (12)

GET/v1/agents

List Agents

POST/v1/agents

Create Agent

// Request body
{
  "name": "string",
  "persona": "string",
  "model_fallback": [],
  "tools": [],
  "skills": [],
  "self_build": {},
  "constraints": {}
}

GET/v1/agents/{agent_id}

Get Agent

PATCH/v1/agents/{agent_id}

Update Agent

DELETE/v1/agents/{agent_id}

Delete Agent

POST/v1/agents/{agent_id}/chat

Agent Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

POST/v1/agents/{agent_id}/memory

Store Memory

// Request body
{
  "content": "string",
  "metadata": {}
}

POST/v1/agents/{agent_id}/memory/query

Query Memory

// Request body
{
  "query": "string",
  "limit": 0
}

GET/v1/agents/{agent_id}/memory/stats

Memory Stats

DELETE/v1/agents/{agent_id}/memory/{memory_id}

Delete Memory

POST/v1/agents/{agent_id}/sub_agents

Create Sub Agent

// Request body
{
  "name": "string",
  "persona": "string",
  "model_fallback": [],
  "tools": [],
  "skills": [],
  "self_build": {},
  "constraints": {}
}

GET/v1/agents/{agent_id}/sub_agents

List Sub Agents

v1/auth (7)

GET/v1/auth/api-keys

List Api Keys

POST/v1/auth/api-keys

Create Api Key

// Request body
{
  "name": "string",
  "scopes": []
}

DELETE/v1/auth/api-keys/{key_id}

Revoke Api Key

POST/v1/auth/logout

Logout

GET/v1/auth/me

Get Me

POST/v1/auth/register

// Request body
{
  "email": "string",
  "name": "string",
  "password": "string",
  "tier": "string"
}

v1/billing (13)

POST/v1/billing/cancel

Cancel Subscription

GET/v1/billing/cards

List Cards

POST/v1/billing/checkout

Create Checkout

// Request body
{
  "tier": "basic"
}

GET/v1/billing/credit

Get Store Credit

POST/v1/billing/credit/transfer

Transfer Affiliate To Credit

GET/v1/billing/history

Payment History

GET/v1/billing/invoices

List Invoices

GET/v1/billing/plans

List Plans V2

GET/v1/billing/status

Billing Status

GET/v1/billing/subscriptions

List Subscriptions

POST/v1/billing/update-payment-method

Update Payment Method

POST/v1/billing/webhook

Square Webhook

v1/catalog (4)

GET/v1/catalog/models

List Models

GET/v1/catalog/models/categories

Model Categories

GET/v1/catalog/models/featured

Featured Models

GET/v1/catalog/models/{model_id}

Get Model

v1/chat (1)

POST/v1/chat/completions

Chat Completions

// Request body
{
  "model": "Qwen/Qwen3-8B",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 100,
  "stream": false
}

v1/clients (4)

GET/v1/clients

List Clients

POST/v1/clients

Create Client

// Request body
{
  "email": "string",
  "name": "string",
  "tier": "string",
  "concurrency_slots": 0,
  "tokens_limit": 0
}

GET/v1/clients/{client_id}

Get Client

PATCH/v1/clients/{client_id}/tier

Update Client Tier

v1/embeddings (1)

POST/v1/embeddings

Create Embeddings

// Request body
{
  "model": "Qwen/Qwen3-Embedding-0.6B",
  "input": "Hello world"
}

v1/events (1)

GET/v1/events

List Events

v1/knowledge-bases (6)

GET/v1/knowledge-bases

List Knowledge Bases

POST/v1/knowledge-bases

Create Knowledge Base

// Request body
{
  "name": "string",
  "description": "string",
  "embedding_model": "string",
  "chunk_size": 0,
  "chunk_overlap": 0
}

GET/v1/knowledge-bases/{kb_id}

Get Knowledge Base

DELETE/v1/knowledge-bases/{kb_id}

Delete Knowledge Base

GET/v1/knowledge-bases/{kb_id}/documents

List Kb Documents

POST/v1/knowledge-bases/{kb_id}/query

Query Knowledge Base

// Request body
{
  "query": "string",
  "limit": 0
}

v1/mcp-servers (4)

GET/v1/mcp-servers

List Mcp Servers

POST/v1/mcp-servers

Create Mcp Server

// Request body
{
  "name": "string",
  "description": "string",
  "code": "string",
  "transport": "string",
  "visibility": "string"
}

GET/v1/mcp-servers/{mcp_id}

Get Mcp Server

DELETE/v1/mcp-servers/{mcp_id}

Delete Mcp Server

v1/models (3)

GET/v1/models

List Models

GET/v1/models/all

List All Featherless Models

GET/v1/models/search

Search Models

v1/skills (4)

GET/v1/skills

List Skills

POST/v1/skills

Create Skill

// Request body
{
  "name": "string",
  "description": "string",
  "tools": [],
  "workflows": [],
  "system_prompt": "string",
  "knowledge": {},
  "visibility": "string"
}

GET/v1/skills/{skill_id}

Get Skill

DELETE/v1/skills/{skill_id}

Delete Skill

v1/subscription (2)

GET/v1/subscription/me

Get My Subscription

GET/v1/subscription/tiers

List Subscription Tiers

v1/tools (4)

GET/v1/tools

List Tools

POST/v1/tools

Create Tool

// Request body
{
  "name": "string",
  "description": "string",
  "code": "string",
  "runtime": "string",
  "input_schema": {},
  "output_schema": {},
  "visibility": "string"
}

GET/v1/tools/{tool_id}

Get Tool

DELETE/v1/tools/{tool_id}

Delete Tool

v1/usage (1)

GET/v1/usage

Get Usage

v1/workflows (6)

GET/v1/workflows

List Workflows

POST/v1/workflows

Create Workflow

// Request body
{
  "name": "string",
  "description": "string",
  "dag": {},
  "trigger": {},
  "persistent": true,
  "resumable": true
}

GET/v1/workflows/{workflow_id}

Get Workflow

DELETE/v1/workflows/{workflow_id}

Delete Workflow

POST/v1/workflows/{workflow_id}/run

Run Workflow

// Request body
{
  "inputs": {}
}

GET/v1/workflows/{workflow_id}/runs

List Workflow Runs

v2/a2a (6)

POST/v2/a2a/broadcast

Broadcast to agents with capability

// Request body
{
  "capability": "string",
  "max_recipients": 0
}

GET/v2/a2a/discover

Discover agents by capability

POST/v2/a2a/tasks

Create A2A Task

// Request body
{
  "target_agent_id": "string",
  "metadata": {}
}

GET/v2/a2a/tasks/{task_id}

Get A2A Task status

POST/v2/a2a/tasks/{task_id}/complete

Complete A2A Task

// Request body
{
  "parts": [],
  "metadata": {}
}

POST/v2/a2a/tasks/{task_id}/send

Send message to A2A Task

// Request body
{
  "task_id": "string",
  "metadata": {}
}

v2/agents (2)

GET/v2/agents/{agent_id}/card

Get Agent A2A Card

PUT/v2/agents/{agent_id}/card

Update Agent A2A Card

// Request body
{
  "name": "string",
  "description": "string",
  "capabilities": [],
  "skills": [],
  "tools": [],
  "model_preference": "string",
  "input_modes": [],
  "output_modes": []
}

v2/improve (2)

POST/v2/improve/build

Auto-Build Tool/Skill/Agent/Workflow

// Request body
{
  "agent_id": "string",
  "need_type": "string",
  "description": "string",
  "auto_register": true
}

POST/v2/improve/search

Search Capabilities

// Request body
{
  "query": "string",
  "types": [],
  "limit": 0
}

v2/spawn (2)

POST/v2/spawn

Multi-Spawn Agents

// Request body
{
  "agents": [],
  "coordinator": true,
  "shared_memory": true,
  "broadcast_results": true
}

GET/v2/spawn/{spawn_id}

Get Spawn Status

v2/status (1)

GET/v2/status

v2 Engine Status

v2/workflows (5)

POST/v2/workflows

Create Persistent Workflow

// Request body
{
  "name": "string",
  "description": "string",
  "steps": [],
  "trigger": {},
  "persistent": true,
  "resumable": true,
  "max_parallel": 0
}

GET/v2/workflows/runs/{run_id}

Get Workflow Run Status

POST/v2/workflows/runs/{run_id}/resume

Resume Crashed Workflow Run

POST/v2/workflows/{workflow_id}/run

Execute Persistent Workflow

// Request body
{
  "inputs": {},
  "metadata": {}
}

GET/v2/workflows/{workflow_id}/runs

List Workflow Runs

v4/agents (6)

POST/v4/agents/{agent_id}/chat

V4 Agent Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

POST/v4/agents/{agent_id}/durable-chat

V4 Durable Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

GET/v4/agents/{agent_id}/session-status

V4 Session Status

GET/v4/agents/{agent_id}/session/history

V4 Session History

POST/v4/agents/{agent_id}/structured-chat

V4 Structured Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

POST/v4/agents/{agent_id}/workflow-chat

V4 Workflow Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

v4/batch (1)

POST/v4/batch

V4 Submit Batch

v4/chat (2)

POST/v4/chat/completions

V1 Chat Completions

POST/v4/chat/detect-task

V4 Detect Task

v4/dlq (3)

GET/v4/dlq

V4 Dlq List

DELETE/v4/dlq/{item_id}

V4 Dlq Delete

POST/v4/dlq/{item_id}/retry

V4 Dlq Retry

v4/embeddings (1)

POST/v4/embeddings

V1 Embeddings

v4/features (5)

GET/v4/features/list

V4 List Features

GET/v4/features/{client_id}

V4 Get Features

POST/v4/features/{client_id}/bulk

V4 Set Features Bulk

POST/v4/features/{client_id}/reset

V4 Reset Features

POST/v4/features/{client_id}/toggle

V4 Set Feature

v4/health (2)

GET/v4/health

V4 Health

GET/v4/health/detailed

V4 Health Detailed

v4/internal (1)

POST/v4/internal/llm

Internal Llm Proxy

v4/mcp (5)

GET/v4/mcp/tools

V4 List Mcp Tools

GET/v4/mcp/tools/list

V4 Mcp Tools List

POST/v4/mcp/tools/register

V4 Register Mcp Tool

DELETE/v4/mcp/tools/{tool_id}

V4 Delete Mcp Tool

POST/v4/mcp/tools/{tool_id}/invoke

V4 Invoke Mcp Tool

v4/models (2)

GET/v4/models

V1 List Models

GET/v4/models/capabilities

V4 Model Capabilities

v4/restate (2)

GET/v4/restate/deployments

V4 Restate Deployments

GET/v4/restate/services

V4 Restate Services

v4/status (1)

GET/v4/status

V4 Status

v4/wasm (4)

GET/v4/wasm/tools

V4 List Wasm Tools

POST/v4/wasm/tools

V4 Register Wasm Tool

DELETE/v4/wasm/tools/{tool_id}

V4 Delete Wasm Tool

POST/v4/wasm/tools/{tool_id}/invoke

V4 Invoke Wasm Tool

v4/workflows (2)

POST/v4/workflows/persistent

V4 Create Persistent Workflow

GET/v4/workflows/persistent/{workflow_id}

V4 Get Persistent Workflow

v5/agents (3)

POST/v5/agents/spawn

Agent Spawn

GET/v5/agents/spawns

Agent List Spawns

GET/v5/agents/spawns/{spawn_id}

Agent Get Spawn

v5/apis (5)

GET/v5/apis/categories

V5 Apis Categories

POST/v5/apis/for-prompt

V5 Apis For Prompt

POST/v5/apis/for-task

V5 Apis For Task

GET/v5/apis/health

V5 Apis Health

POST/v5/apis/search

V5 Apis Search

v5/episodes (4)

POST/v5/episodes/batch

V5 Episode Batch

POST/v5/episodes/entity

V5 Episode Get Entity

POST/v5/episodes/ingest

V5 Episode Ingest

POST/v5/episodes/temporal-facts

V5 Episode Temporal Facts

v5/events (6)

POST/v5/events

Event Append

GET/v5/events

Event Query

GET/v5/events/health

Event Health

GET/v5/events/replay/{entity_type}/{entity_id}

Event Replay

GET/v5/events/stats

Event Stats

POST/v5/events/trim

Event Trim

v5/facts (4)

POST/v5/facts/batch-extract

Fact Batch Extract

POST/v5/facts/extract

Fact Extract

POST/v5/facts/extract-and-store

Fact Extract And Store

POST/v5/facts/extract-turn

Fact Extract Turn

v5/guardrails (7)

POST/v5/guardrails/check

Gr Check

GET/v5/guardrails/health

Gr Health

GET/v5/guardrails/logs

Gr Get Logs

POST/v5/guardrails/rules

Gr Create Rule

GET/v5/guardrails/rules

Gr List Rules

GET/v5/guardrails/rules/{name}

Gr Get Rule

DELETE/v5/guardrails/rules/{name}

Gr Delete Rule

v5/hubs (17)

GET/v5/hubs/knowledge/books

Knowledge Hub Books

GET/v5/hubs/knowledge/general

Knowledge Hub General

GET/v5/hubs/knowledge/health

Knowledge Hub Health

GET/v5/hubs/knowledge/papers

Knowledge Hub Papers

GET/v5/hubs/knowledge/search

Knowledge Hub Search

GET/v5/hubs/skills/fetch/{skill_id}

Skills Hub Fetch

GET/v5/hubs/skills/health

Skills Hub Health

GET/v5/hubs/skills/search

Skills Hub Search

GET/v5/hubs/skills/sources

Skills Hub Sources

GET/v5/hubs/skills/top

Skills Hub Top

GET/v5/hubs/tools/categories

Tools Hub Categories

GET/v5/hubs/tools/health

Tools Hub Health

GET/v5/hubs/tools/search

Tools Hub Search

GET/v5/hubs/workflows/categories

Workflows Hub Categories

GET/v5/hubs/workflows/health

Workflows Hub Health

GET/v5/hubs/workflows/live

Workflows Hub Live

GET/v5/hubs/workflows/search

Workflows Hub Search

v5/intent (1)

POST/v5/intent/classify

Intent Classify

v5/kg (7)

POST/v5/kg/auto-build

Kg Auto Build

POST/v5/kg/entities

V5 Kg Add Entity

GET/v5/kg/entities

V5 Kg List Entities

GET/v5/kg/health

V5 Kg Health

POST/v5/kg/relations

V5 Kg Add Relation

POST/v5/kg/search

V5 Kg Search

GET/v5/kg/stats

V5 Kg Stats

v5/ks (4)

POST/v5/ks/articles

V5 Ks Search Articles

POST/v5/ks/books

V5 Ks Search Books

POST/v5/ks/enrich

V5 Ks Enrich

GET/v5/ks/health

V5 Ks Health

v5/learning (1)

POST/v5/learning/evaluate

Self Evaluate

v5/mcp (7)

GET/v5/mcp/categories

Mcp Hub Categories

POST/v5/mcp/ingest

Mcp Hub Ingest

POST/v5/mcp/register

Mcp Hub Register

POST/v5/mcp/search

Mcp Hub Search

GET/v5/mcp/stats

Mcp Hub Stats

GET/v5/mcp/{catalog_id}

Mcp Hub Get

DELETE/v5/mcp/{catalog_id}

Mcp Hub Delete

v5/memory (14)

POST/v5/memory/archival/{agent_id}

Tier Archival Insert

POST/v5/memory/archival/{agent_id}/search

Tier Archival Search

POST/v5/memory/consolidate/{agent_id}

Tier Consolidate

GET/v5/memory/context/{agent_id}

Tier Build Context

GET/v5/memory/core/{agent_id}

Tier Core Get

POST/v5/memory/core/{agent_id}

Tier Core Append

PUT/v5/memory/core/{agent_id}

Tier Core Replace

DELETE/v5/memory/core/{agent_id}

Tier Core Delete

POST/v5/memory/promote

Tier Promote

POST/v5/memory/recall/{agent_id}

Tier Recall Add

GET/v5/memory/recall/{agent_id}/recent

Tier Recall Recent

POST/v5/memory/recall/{agent_id}/search

Tier Recall Search

GET/v5/memory/stats/{agent_id}

Tier Stats

POST/v5/memory/temporal-search

Temporal Memory Search

v5/observability (8)

GET/v5/observability/database

Obs Db Stats

GET/v5/observability/errors

Obs Errors

GET/v5/observability/health

Obs Health

GET/v5/observability/metrics

Obs Metrics

GET/v5/observability/restate

Obs Restate

POST/v5/observability/snapshot

Obs Snapshot

GET/v5/observability/snapshots

Obs Snapshots

GET/v5/observability/usage

Obs Usage

v5/pipelines (6)

POST/v5/pipelines

Pipeline Create

GET/v5/pipelines

Pipeline List

GET/v5/pipelines/{name}

Pipeline Get

DELETE/v5/pipelines/{name}

Pipeline Delete

POST/v5/pipelines/{name}/run

Pipeline Execute

GET/v5/pipelines/{name}/runs

Pipeline List Runs

v5/plugins (11)

GET/v5/plugins/categories

Plugin Categories

POST/v5/plugins/find-for-task

Plugin Find For Task

POST/v5/plugins/ingest

Plugin Ingest

POST/v5/plugins/invoke/{plugin_id}

Plugin Invoke

GET/v5/plugins/list

Plugin List

POST/v5/plugins/register

Plugin Register

POST/v5/plugins/search

Plugin Search

GET/v5/plugins/sources

Plugin Sources

GET/v5/plugins/stats

Plugin Stats

GET/v5/plugins/{plugin_id}

Plugin Get

DELETE/v5/plugins/{plugin_id}

Plugin Delete

v5/rate-limits (6)

GET/v5/rate-limits/check

Rate Limit Check

POST/v5/rate-limits/cleanup

Rate Limit Cleanup

GET/v5/rate-limits/config/{api_key}

Rate Limit Get Config

POST/v5/rate-limits/configure

Rate Limit Configure

POST/v5/rate-limits/increment

Rate Limit Increment

GET/v5/rate-limits/tiers

Rate Limit Tiers

v5/schedule (7)

POST/v5/schedule

Sched Create

GET/v5/schedule

Sched List

GET/v5/schedule/runs

Sched Runs

POST/v5/schedule/tick

Sched Tick

GET/v5/schedule/{name}

Sched Get

DELETE/v5/schedule/{name}

Sched Delete

POST/v5/schedule/{name}/cancel

Sched Cancel

v5/skills (5)

POST/v5/skills/fetch

V5 Skills Fetch

POST/v5/skills/for-prompt

V5 Skills For Prompt

GET/v5/skills/health

V5 Skills Health

GET/v5/skills/packs

V5 Skills List Packs

POST/v5/skills/resolve

V5 Skills Resolve

v5/summarize (2)

POST/v5/summarize/agent/{agent_id}

Summarize Agent

POST/v5/summarize/messages

Summarize Messages

v5/templates (8)

POST/v5/templates

Template Create

GET/v5/templates

Template List

GET/v5/templates/analytics

Template Analytics

POST/v5/templates/runs

Template Record Run

GET/v5/templates/{name}

Template Get

DELETE/v5/templates/{name}

Template Delete

POST/v5/templates/{name}/render

Template Render

GET/v5/templates/{name}/variant

Template Resolve Variant

v5/tools (7)

POST/v5/tools/generate

Tool Generate

POST/v5/tools/generate-from-url

Tool Generate From Url

GET/v5/tools/generated

Tool List Generated

GET/v5/tools/generated/{name}

Tool Get Generated

DELETE/v5/tools/generated/{name}

Tool Delete Generated

POST/v5/tools/prefilter

Tool Prefilter

POST/v5/tools/prefilter-context

Tool Prefilter Context

v5/tot (2)

POST/v5/tot/quick

Tot Quick

POST/v5/tot/reason

Tot Reason

v5/usage (2)

POST/v5/usage/record

Usage Record

GET/v5/usage/{api_key}

Usage Get

v5/workflows (6)

POST/v5/workflows

Workflow Create

GET/v5/workflows

Workflow List

GET/v5/workflows/{name}

Workflow Get

DELETE/v5/workflows/{name}

Workflow Delete

POST/v5/workflows/{name}/run

Workflow Execute

GET/v5/workflows/{name}/runs

Workflow List Runs

Intelligence API (api.openrout.ing) (20)

GET/v1/system-status

System Status

GET/v1/agents

List Agents (904)

GET/v1/agents/{agent_id}

Get Agent

POST/v1/agents/create

Create Agent

POST/v1/agents/{agent_id}/chat

Agent Chat

// Request body
{
  "message": "What is your role?",
  "context": "general"
}

GET/v1/agents/{agent_id}/recall

Recall Memory

POST/v1/agents/{agent_id}/remember

Store Memory

GET/v1/workflows

List Workflows

POST/v1/workflows/{template_id}/execute

Execute Workflow

POST/v1/delegate

Delegate Task

POST/v1/collaborate

Collaborate

GET/v1/marketplace

List Marketplace

GET/v1/health-check

Health Check

GET/v1/keys/verify

Verify Key

GET/v1/reputation

Reputation

POST/v1/abtest/create

Create A/B Test

GET/v1/heatmap

Agent Heatmap

GET/v1/costs

Cost Analysis

GET/v1/performance

Performance