### OpenAI SDK Streaming Request with BrainstormRouter

Source: https://docs.brainstormrouter.com/concepts/streaming-security

Demonstrates how to use the OpenAI Python SDK to send a streaming request to the BrainstormRouter API. This example shows the client-side setup and how to iterate through the streamed response chunks.

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.brainstormrouter.com/v1",
    api_key="br_live_...",
)

stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-4",
    messages=[{"role": "user", "content": "Summarize the customer file for Acme Corp."}],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
```

--------------------------------

### Get Specific Observability Integration Template

Source: https://docs.brainstormrouter.com/api-reference/observability

Fetches the configuration schema, recommended event types, and an example configuration for a specific observability integration template, such as 'langfuse'.

```curl
curl https://api.brainstormrouter.com/v1/observability/templates/langfuse \
  -H "Authorization: Bearer br_live_..."
```

--------------------------------

### List Models API Example (cURL)

Source: https://brainstormrouter.com/llms-full.txt

This example shows how to list available models using cURL. It requires setting the Authorization header with a Bearer token to authenticate the request to the /v1/models endpoint.

```bash
curl https://api.brainstormrouter.com/v1/models \
  -H "Authorization: Bearer brk_your_key"
```

--------------------------------

### Use BrainstormRouter Model Variants with Vercel AI SDK (JavaScript)

Source: https://docs.brainstormrouter.com/guides/vercel-ai

Illustrates how to use different routing variants of BrainstormRouter models directly with the Vercel AI SDK. Examples include 'floor', 'fast', and 'best' variants.

```javascript
const cheap = brainstorm("openai/gpt-4o-mini:floor");
const fast = brainstorm("anthropic/claude-haiku-4-5:fast");
const best = brainstorm("anthropic/claude-sonnet-4:best");
```

--------------------------------

### List Available Models - Response Example

Source: https://docs.brainstormrouter.com/api-reference/models

Example JSON response from the `/v1/models` endpoint. It includes a list of models, each with an ID, object type, creation timestamp, and the owning provider.

```json
{
  "object": "list",
  "data": [
    {
      "id": "anthropic/claude-sonnet-4",
      "object": "model",
      "created": 1700000000,
      "owned_by": "anthropic"
    },
    {
      "id": "openai/gpt-4o",
      "object": "model",
      "created": 1700000000,
      "owned_by": "openai"
    }
  ]
}
```

--------------------------------

### Error Reference

Source: https://docs.brainstormrouter.com/start/quickstart

Provides details on status codes and error bodies for the API.

```APIDOC
## GET /api-reference/errors

### Description
Retrieves a reference of all possible API errors, including status codes and their corresponding error response bodies.

### Method
GET

### Endpoint
/api-reference/errors

### Parameters
#### Query Parameters
None

### Request Example
```json
{
  "example": "No request body needed for this GET request."
}
```

### Response
#### Success Response (200)
- **statusCode** (integer) - The HTTP status code associated with the error.
- **errorBody** (object) - A description of the error response body structure.

#### Response Example
```json
{
  "example": [
    {
      "statusCode": 400,
      "errorBody": {
        "code": "INVALID_INPUT",
        "message": "The provided input is invalid."
      }
    },
    {
      "statusCode": 404,
      "errorBody": {
        "code": "RESOURCE_NOT_FOUND",
        "message": "The requested resource could not be found."
      }
    }
  ]
}
```
```

--------------------------------

### Chat Completion API Example (cURL)

Source: https://brainstormrouter.com/llms-full.txt

This example demonstrates how to perform a chat completion request using cURL. It includes setting the Authorization header with a Bearer token, specifying the content type, and providing a JSON payload with the model, messages, and stream options.

```bash
curl -X POST https://api.brainstormrouter.com/v1/chat/completions \
  -H "Authorization: Bearer brk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'
```

--------------------------------

### Observability Templates and Testing

Source: https://brainstormrouter.com/llms-full.txt

This API route provides access to observability templates and allows for testing observability configurations. API Key authentication is required. Use GET /v1/observability/templates to retrieve templates and GET /v1/observability/templates/:provider to get templates for a specific provider. POST /v1/observability/test/:id tests a specific configuration.

```http
GET /v1/observability/templates
```

```http
GET /v1/observability/templates/:provider
```

```http
POST /v1/observability/test/:id
```

--------------------------------

### Agentic Chat Completion with Memory - Python Example

Source: https://docs.brainstormrouter.com/concepts/memory

Demonstrates how to interact with an agentic chat completion API, showing how the agent can be 'taught' information and later recall it. This highlights the tenant-wide memory scoping where conversation history is not explicitly passed.

```python
client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Our deploy target is us-east-1 on ECS Fargate." }],
    extra_body={"mode": "agentic"},
)

client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Where do we deploy?" }],
    extra_body={"mode": "agentic"},
)
# → "You deploy to us-east-1 on ECS Fargate."
```

--------------------------------

### CrewAI Setup and Configuration with BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/crewai

Install necessary libraries and configure environment variables to point CrewAI's underlying OpenAI SDK to the BrainstormRouter API endpoint. This allows CrewAI to leverage BrainstormRouter's routing capabilities.

```python
pip install crewai openai brainstormrouter

import os

os.environ["OPENAI_API_BASE"] = "https://api.brainstormrouter.com/v1"
os.environ["OPENAI_API_KEY"] = "br_live_..."
```

--------------------------------

### Model Leaderboard - Response Example

Source: https://docs.brainstormrouter.com/api-reference/models

Example JSON response from the `/v1/models/leaderboard` endpoint. It provides detailed performance metrics for models, including reward scores, quality, latency, pricing, and capabilities, sorted by a specified dimension.

```json
{
  "object": "list",
  "sort_by": "overall",
  "model_count": 42,
  "cached_at": "2026-02-26T12:00:00.000Z",
  "data": [
    {
      "id": "anthropic/claude-sonnet-4",
      "provider": "anthropic",
      "model_id": "claude-sonnet-4",
      "reward_score": 0.8523,
      "reward_variance": 0.0012,
      "validity": 0.9501,
      "quality": 0.91,
      "latency_ms": 520.3,
      "tokens_per_second": 85.2,
      "success_rate": 0.998,
      "pricing": { "input": 3, "output": 15 },
      "capabilities": ["streaming", "tools", "vision"],
      "sample_count": 12430,
      "days_active": 7,
      "error_rate": 0.002,
      "value_score": 284.1
    }
  ]
}
```

--------------------------------

### Create a Reusable Preset in JavaScript

Source: https://docs.brainstormrouter.com/concepts/routing

Illustrates how to create a reusable preset configuration in JavaScript, defining a default model, strategy, fallbacks, and cost limits. Presets simplify complex routing setups.

```javascript
await client.presets.create({
  slug: "production",
  name: "Production Config",
  model: "anthropic/claude-sonnet-4",
  strategy: "quality",
  fallbacks: ["openai/gpt-4o", "google/gemini-2.0-flash"],
  max_cost_usd: 0.50,
});
```

--------------------------------

### LangChain Streaming Responses with BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/langchain

Demonstrates how to stream responses from a LangChain model configured with BrainstormRouter. This allows for real-time display of LLM output as it's generated. Requires '@langchain/openai'.

```typescript
const stream = await model.stream("Write a haiku about APIs");
for await (const chunk of stream) {
  process.stdout.write(chunk.content as string);
}
```

--------------------------------

### Perform RAG with LlamaIndex and BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/llamaindex

Demonstrates how to set up a Retrieval Augmented Generation (RAG) pipeline using LlamaIndex with BrainstormRouter as the LLM. It involves loading documents, creating an index, and querying the index.

```python
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Load documents
documents = SimpleDirectoryReader("./docs").load_data()
index = VectorStoreIndex.from_documents(documents, llm=llm)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("What is the main architecture pattern?")
print(response)
```

--------------------------------

### LangChain Basic Usage with BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/langchain

Demonstrates how to configure LangChain's ChatOpenAI integration to use BrainstormRouter as its LLM backend by setting a custom baseURL. Requires the '@langchain/openai' and 'brainstormrouter' npm packages.

```typescript
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  configuration: {
    baseURL: "https://api.brainstormrouter.com/v1",
  },
  apiKey: "br_live_...",
  model: "anthropic/claude-sonnet-4",
});

const response = await model.invoke("Explain quantum computing");
console.log(response.content);
```

--------------------------------

### Fetch Model Leaderboard using cURL

Source: https://docs.brainstormrouter.com/api-reference/models

This example demonstrates how to retrieve the model leaderboard using a cURL command. It specifies the sorting dimension ('overall') and a limit for the number of results, requiring an API key for authentication.

```bash
curl "https://api.brainstormrouter.com/v1/models/leaderboard?sort=overall&limit=10" \
  -H "Authorization: Bearer br_live_..."
```

--------------------------------

### Configure Fallback Chain in JSON

Source: https://docs.brainstormrouter.com/concepts/routing

Provides an example of configuring fallback models for a chat completion request in JSON format. This ensures that if the primary model fails, the router attempts alternative models in a specified order.

```json
{
  "model": "anthropic/claude-sonnet-4",
  "route": {
    "fallbacks": ["openai/gpt-4o", "google/gemini-2.0-flash"],
    "strategy": "priority"
  }
}
```

--------------------------------

### Integrate BrainstormRouter Memory with Vercel AI SDK (JavaScript)

Source: https://docs.brainstormrouter.com/guides/vercel-ai

Demonstrates pre-loading BrainstormRouter memory and using it with the Vercel AI SDK for agentic mode. Memory is initialized once and then used implicitly by the model.

```javascript
import BrainstormRouter from "brainstormrouter";
import { streamText } from "ai";
import { createOpenAI } from "@ai-sdk/openai";

const brainstorm = createOpenAI({
  baseURL: "https://api.brainstormrouter.com/v1",
  apiKey: process.env.BRAINSTORMROUTER_API_KEY!,
});

// Bootstrap memory once
const br = new BrainstormRouter();
await br.memory.init([{ content: "Company: Acme Corp. Product: Widget Pro.", source: "about.md" }]);

// Vercel AI SDK uses the enriched model
const result = streamText({
  model: brainstorm("anthropic/claude-sonnet-4"),
  messages: [{ role: "user", content: "What product does the company sell?" }],
  // Pass mode via headers or body extension
});
```

--------------------------------

### LangChain Tool Calling with BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/langchain

Illustrates how to enable tool calling functionality in LangChain when using BrainstormRouter. This involves defining tools with descriptions and schemas, then binding them to the LangChain model. Requires '@langchain/openai', '@langchain/core', and 'zod'.

```typescript
import { ChatOpenAI } from "@langchain/openai";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const weatherTool = tool(async ({ city }) => `72°F and sunny in ${city}`, {
  name: "get_weather",
  description: "Get weather for a city",
  schema: z.object({ city: z.string() }),
});

const model = new ChatOpenAI({
  configuration: { baseURL: "https://api.brainstormrouter.com/v1" },
  apiKey: "br_live_...",
  model: "anthropic/claude-sonnet-4",
}).bindTools([weatherTool]);

const response = await model.invoke("What's the weather in San Francisco?");
```

--------------------------------

### Generate Text with BrainstormRouter and Vercel AI SDK (JavaScript)

Source: https://docs.brainstormrouter.com/guides/vercel-ai

Demonstrates how to generate text using the BrainstormRouter model via the Vercel AI SDK. It takes a model identifier and a prompt, returning the generated text.

```javascript
import { generateText } from "ai";

const { text } = await generateText({
  model: brainstorm("anthropic/claude-sonnet-4"),
  prompt: "Explain quantum computing in one paragraph.",
});
```

--------------------------------

### Configure BrainstormRouter Provider with Vercel AI SDK (JavaScript)

Source: https://docs.brainstormrouter.com/guides/vercel-ai

Sets up the BrainstormRouter provider for use with the Vercel AI SDK. It requires the `ai` and `@ai-sdk/openai` packages and configures the base URL and API key for BrainstormRouter.

```javascript
import { createOpenAI } from "@ai-sdk/openai";

const brainstorm = createOpenAI({
  baseURL: "https://api.brainstormrouter.com/v1",
  apiKey: "br_live_...",
});
```

--------------------------------

### Enable Streaming Responses in LlamaIndex with BrainstormRouter

Source: https://docs.brainstormrouter.com/guides/llamaindex

Shows how to enable streaming responses from LlamaIndex queries when using BrainstormRouter. This allows for real-time token generation, improving user experience for interactive applications.

```python
from llama_index.core import Settings

Settings.llm = llm

query_engine = index.as_query_engine(streaming=True)
response = query_engine.query("Summarize the key findings")

for token in response.response_gen:
    print(token, end="", flush=True)
```

--------------------------------

### Send First Chat Completion Request (Python)

Source: https://docs.brainstormrouter.com/start/quickstart

This Python snippet demonstrates how to send a chat completion request to BrainstormRouter using the OpenAI SDK. It requires the `openai` library and an API key. The output is the content of the model's response.

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.brainstormrouter.com/v1",
    api_key="br_live_...",
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Explain quantum computing in one paragraph."}]
)

print(response.choices[0].message.content)
```

--------------------------------

### Send First Chat Completion Request (OpenAI SDK - JavaScript)

Source: https://docs.brainstormrouter.com/start/quickstart

This JavaScript snippet uses the standard OpenAI SDK to interact with BrainstormRouter. It requires the `openai` library and an API key, with the `baseURL` set to the BrainstormRouter endpoint. The output is the content of the model's response.

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.brainstormrouter.com/v1",
  apiKey: "br_live_...",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Explain quantum computing in one paragraph." }],
});

console.log(response.choices[0].message.content);
```

--------------------------------

### Store RAG Insights in BrainstormRouter Memory

Source: https://docs.brainstormrouter.com/guides/llamaindex

This example illustrates how to store insights discovered during a RAG process into BrainstormRouter's persistent memory. It uses the `requests` library to make a POST request to the memory entries endpoint.

```python
import requests

# Store RAG-discovered insights in persistent memory
requests.post(
    "https://api.brainstormrouter.com/v1/memory/entries",
    headers={"Authorization": "Bearer br_live_..."},
    json={
        "fact": "Architecture uses event-driven microservices with Kafka",
        "block": "project",
    },
)
```

--------------------------------

### Send First Chat Completion Request (cURL)

Source: https://docs.brainstormrouter.com/start/quickstart

This cURL command demonstrates how to send a chat completion request to BrainstormRouter from the command line. It requires an API key and specifies the model and messages in JSON format. The response contains the model's output.

```bash
curl https://api.brainstormrouter.com/v1/chat/completions \
  -H "Authorization: Bearer br_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Explain quantum computing in one paragraph."}]
  }'
```

--------------------------------

### Configure LlamaIndex with BrainstormRouter LLM

Source: https://docs.brainstormrouter.com/guides/llamaindex

This snippet shows how to configure LlamaIndex to use BrainstormRouter as an OpenAI-compatible LLM provider. It requires installing the `llama-index-llms-openai-like` package and setting the API base URL, API key, and desired model.

```python
from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    api_base="https://api.brainstormrouter.com/v1",
    api_key="br_live_...",
    model="anthropic/claude-sonnet-4",
    is_chat_model=True,
)
```

--------------------------------

### Use Auto Routing for Chat Completion (cURL)

Source: https://docs.brainstormrouter.com/start/quickstart

This cURL command demonstrates how to use auto routing for chat completions by setting the `model` parameter to `"auto"`. BrainstormRouter will then select the best model based on request complexity, cost budget, and learned quality scores.

```bash
curl https://api.brainstormrouter.com/v1/chat/completions \
  -H "Authorization: Bearer br_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "What is 2+2?"}]
  }'
```

--------------------------------

### Send First Chat Completion Request (JavaScript)

Source: https://docs.brainstormrouter.com/start/quickstart

This JavaScript snippet shows how to send a chat completion request to BrainstormRouter using a custom BrainstormRouter SDK. It requires the `brainstormrouter` library and an API key. It also demonstrates appending memory to the conversation.

```javascript
import BrainstormRouter from "brainstormrouter";

const client = new BrainstormRouter({ apiKey: "br_live_..." });

const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Explain quantum computing in one paragraph." }],
});

console.log(response.choices[0].message.content);

// Plus: memory, guardrails, governance, and more
await client.memory.append("User asked about quantum computing", { block: "general" });
```

--------------------------------

### Retrieve Memory Blocks

Source: https://brainstormrouter.com/llms-full.txt

This API route allows retrieval of memory blocks. API Key authentication is required. Use a GET request to /v1/memory/blocks to get all blocks, or /v1/memory/blocks/:block to get a specific block.

```http
GET /v1/memory/blocks
```

```http
GET /v1/memory/blocks/:block
```

--------------------------------

### Get Health Status

Source: https://brainstormrouter.com/llms-full.txt

This API route retrieves the health status of the BrainstormRouter service. It does not require any authentication. The GET request should be made to the /health endpoint.

```http
GET /health
```

--------------------------------

### Get OpenAPI Specification

Source: https://brainstormrouter.com/llms-full.txt

This API route provides the OpenAPI specification for the BrainstormRouter API. No authentication is required. Send a GET request to the /openapi.json endpoint to retrieve the specification.

```http
GET /openapi.json
```

--------------------------------

### Configure Batched Webhook Destination (JavaScript)

Source: https://docs.brainstormrouter.com/concepts/observability

Illustrates setting up a webhook destination with batching enabled to reduce HTTP overhead. This configuration specifies the maximum number of events per batch and the flush interval in milliseconds.

```javascript
    await client.observability.addDestination({
      name: "Analytics",
      type: "webhook",
      config: { url: "https://analytics.example.com/ingest" },
      batch: {
        max_size: 100, // flush after 100 events
        flush_interval_ms: 5000, // or every 5 seconds
      },
    });
```

--------------------------------

### LangChain Multi-Model Comparison with BrainstormRouter Presets

Source: https://docs.brainstormrouter.com/guides/langchain

Shows how to use BrainstormRouter's preset feature within LangChain to perform A/B testing or compare different LLM models easily. This is achieved by specifying preset model names in the LangChain configuration. Requires '@langchain/openai'.

```typescript
const cheap = new ChatOpenAI({
  configuration: { baseURL: "https://api.brainstormrouter.com/v1" },
  apiKey: "br_live_...",
  model: "@preset/fast-cheap",
});

const quality = new ChatOpenAI({
  configuration: { baseURL: "https://api.brainstormrouter.com/v1" },
  apiKey: "br_live_...",
  model: "@preset/high-quality",
});
```

--------------------------------

### Simulate Routing Strategies via cURL

Source: https://docs.brainstormrouter.com/concepts/routing

Shows how to use the Replays API with cURL to simulate different routing strategies over a specified time period. This is useful for analyzing historical performance and cost.

```shell
curl https://api.brainstormrouter.com/v1/replays/simulate \
  -H "Authorization: Bearer br_live_..." \
  -d '{"strategy": "price", "since": "2025-02-20T00:00:00Z"}'
```

--------------------------------

### Get Model Leaderboard

Source: https://brainstormrouter.com/llms-full.txt

This API route provides access to the model leaderboard, ranking models based on performance metrics. API Key authentication is required. Send a GET request to the /v1/models/leaderboard endpoint.

```http
GET /v1/models/leaderboard
```

--------------------------------

### Thread Conversations with Conversation ID (Python)

Source: https://docs.brainstormrouter.com/start/quickstart

This Python snippet demonstrates how to maintain context across multiple chat completion requests by using a `conversation_id`. The first request sets the context (e.g., remembering a name), and subsequent requests in the same conversation can refer to it.

```python
response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Remember that my name is Alice." }],
    extra_body={"conversation_id": "session-123"},
)

# Later, same conversation:
response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "What's my name?" }],
    extra_body={"conversation_id": "session-123"},
)
```

--------------------------------

### Manage Guardrail Configurations

Source: https://brainstormrouter.com/llms-full.txt

This API route allows for the management of guardrail configurations, including retrieving, updating, and managing providers. API Key authentication is required. Endpoints include GET /v1/guardrails/config, PUT /v1/guardrails/config, GET /v1/guardrails/providers, POST /v1/guardrails/providers, and DELETE /v1/guardrails/providers/:id.

```http
GET /v1/guardrails/config
```

```http
PUT /v1/guardrails/config
```

```http
GET /v1/guardrails/providers
```

```http
POST /v1/guardrails/providers
```

```http
DELETE /v1/guardrails/providers/:id
```

--------------------------------

### Initialize and Use BrainstormRouter SDK

Source: https://brainstormrouter.com/llms-full.txt

Instantiate the BrainstormRouter client with an API key and use it to create chat completions. Supports multiple programming languages.

```bash
npm install brainstormrouter
```

```typescript
import { BrainstormRouter } from "brainstormrouter";
const br = new BrainstormRouter({ apiKey: "brk_..." });
const result = await br.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Hello" }],
});
```

```bash
pip install brainstormrouter
```

```python
from brainstormrouter import BrainstormRouter
br = BrainstormRouter(api_key="brk_...")
result = br.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello"}],
)
```

--------------------------------

### Manage Presets

Source: https://brainstormrouter.com/llms-full.txt

This API route allows for the management of presets, including creation, retrieval, updates, and deletion. API Key authentication is required. Endpoints include POST /v1/presets, GET /v1/presets, GET /v1/presets/:slug, PUT /v1/presets/:slug, and DELETE /v1/presets/:slug.

```http
POST /v1/presets
```

```http
GET /v1/presets
```

```http
GET /v1/presets/:slug
```

```http
PUT /v1/presets/:slug
```

```http
DELETE /v1/presets/:slug
```

--------------------------------

### GET /v1/providers/catalog

Source: https://brainstormrouter.com/llms-full.txt

Retrieves the provider catalog. This endpoint provides access to the provider catalog.

```APIDOC
## GET /v1/providers/catalog

### Description
Retrieves the provider catalog.

### Method
GET

### Endpoint
/v1/providers/catalog

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **catalog** (object) - The provider catalog data.

#### Response Example
{
  "catalog": {
    "providers": [{"name": "OpenAI", "type": "llm"}]
  }
}
```

--------------------------------

### GET /v1/governance/summary

Source: https://brainstormrouter.com/llms-full.txt

Retrieves a governance summary. This endpoint provides a summary of governance-related information.

```APIDOC
## GET /v1/governance/summary

### Description
Retrieves a governance summary.

### Method
GET

### Endpoint
/v1/governance/summary

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **summary** (object) - Governance summary data.

#### Response Example
{
  "summary": {
    "status": "ok",
    "details": "System is running smoothly"
  }
}
```

--------------------------------

### Reference a Preset in Chat Completion in JavaScript

Source: https://docs.brainstormrouter.com/concepts/routing

Demonstrates how to reference a previously created preset using its slug in a chat completion request. This applies the saved routing configuration to the request.

```javascript
await client.chat.completions.create({
  model: "@preset/production",
  messages: [...],
});
```

--------------------------------

### GET /v1/governance/behavioral-profiles

Source: https://brainstormrouter.com/llms-full.txt

Retrieves behavioral profiles. This endpoint allows fetching behavioral profiles.

```APIDOC
## GET /v1/governance/behavioral-profiles

### Description
Retrieves behavioral profiles.

### Method
GET

### Endpoint
/v1/governance/behavioral-profiles

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **profiles** (array) - An array of behavioral profile objects.

#### Response Example
{
  "profiles": [
    {
      "role": "user",
      "profile": {"behavior": "example"}
    }
  ]
}
```

--------------------------------

### GET /v1/governance/anomaly/scores

Source: https://brainstormrouter.com/llms-full.txt

Retrieves anomaly scores. This endpoint provides access to the scores of anomalies.

```APIDOC
## GET /v1/governance/anomaly/scores

### Description
Retrieves anomaly scores.

### Method
GET

### Endpoint
/v1/governance/anomaly/scores

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **scores** (array) - An array of anomaly score objects.

#### Response Example
{
  "scores": [
    {
      "metric": "metric1",
      "score": 0.75
    }
  ]
}
```

--------------------------------

### CrewAI Cost Optimization with BrainstormRouter Presets

Source: https://docs.brainstormrouter.com/guides/crewai

Utilize BrainstormRouter's preset system to automatically select models based on cost and quality strategies. This example shows assigning a 'high-quality' preset to a research agent and a 'fast-cheap' preset to a formatter agent.

```python
# Expensive tasks get the quality model
researcher = Agent(
    role="Research Analyst",
    llm="@preset/high-quality",  # anthropic/claude-sonnet-4, quality strategy
)

# Simple tasks get the cheap model
formatter = Agent(
    role="Formatter",
    llm="@preset/fast-cheap",  # openai/gpt-4o-mini, price strategy
)
```

--------------------------------

### GET /v1/governance/anomaly/history

Source: https://brainstormrouter.com/llms-full.txt

Retrieves anomaly history. This endpoint provides access to the history of anomalies.

```APIDOC
## GET /v1/governance/anomaly/history

### Description
Retrieves the history of anomalies.

### Method
GET

### Endpoint
/v1/governance/anomaly/history

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **history** (array) - An array of anomaly history objects.

#### Response Example
{
  "history": [
    {
      "timestamp": "2024-01-01T00:00:00Z",
      "description": "Anomaly Description"
    }
  ]
}
```

--------------------------------

### GET /v1/mcp/tools

Source: https://brainstormrouter.com/llms-full.txt

Retrieves available tools for MCP. This endpoint provides a list of available tools.

```APIDOC
## GET /v1/mcp/tools

### Description
Retrieves available tools for MCP.

### Method
GET

### Endpoint
/v1/mcp/tools

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **tools** (array) - An array of available tool objects.

#### Response Example
{
  "tools": [
    {
      "toolId": "tool1",
      "name": "Example Tool"
    }
  ]
}
```

--------------------------------

### List Observability Integration Templates

Source: https://docs.brainstormrouter.com/api-reference/observability

Retrieves a list of available integration templates for various observability platforms. These templates simplify configuration by providing pre-filled schemas and recommended settings.

```curl
curl https://api.brainstormrouter.com/v1/observability/templates \
  -H "Authorization: Bearer br_live_..."
```

--------------------------------

### GET /v1/mcp/connect

Source: https://brainstormrouter.com/llms-full.txt

Retrieves the MCP connection status. This endpoint provides the current connection status.

```APIDOC
## GET /v1/mcp/connect

### Description
Retrieves the MCP connection status.

### Method
GET

### Endpoint
/v1/mcp/connect

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **connection_status** (string) - The connection status.

#### Response Example
{
  "connection_status": "connected"
}
```

--------------------------------

### Enable Agentic Mode for Chat Completion

Source: https://docs.brainstormrouter.com/start/quickstart

This Python snippet shows how to enable agentic mode for a chat completion request by adding `"mode": "agentic"` to the `extra_body`. Agentic mode utilizes BrainstormRouter's autonomous agent engine with built-in memory and tool use.

```python
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Summarize yesterday's findings and suggest next steps." }],
    extra_body={"mode": "agentic"},
)
```

--------------------------------

### GET /v1/providers

Source: https://brainstormrouter.com/llms-full.txt

Retrieves a list of providers. This endpoint allows fetching a list of available providers.

```APIDOC
## GET /v1/providers

### Description
Retrieves a list of providers.

### Method
GET

### Endpoint
/v1/providers

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **providers** (array) - An array of provider objects.

#### Response Example
{
  "providers": [
    {
      "providerId": "provider123",
      "name": "OpenAI",
      "type": "llm"
    }
  ]
}
```

--------------------------------

### GET /v1/governance/memory/stats

Source: https://brainstormrouter.com/llms-full.txt

Retrieves memory statistics. This endpoint provides access to memory usage statistics.

```APIDOC
## GET /v1/governance/memory/stats

### Description
Retrieves memory statistics.

### Method
GET

### Endpoint
/v1/governance/memory/stats

### Parameters

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **memory_stats** (object) - Memory usage statistics.

#### Response Example
{
  "memory_stats": {
    "used": 1024,
    "available": 4096
  }
}
```

--------------------------------

### Bootstrap Memory from Documents using cURL

Source: https://docs.brainstormrouter.com/api-reference/memory

This cURL command shows how to bootstrap agent memory by extracting facts from provided documents. It utilizes an LLM to analyze content and assign facts to appropriate memory blocks. Requires authentication, JSON content type, and a list of documents with their content and source, along with a specified model.

```shell
curl -X POST https://api.brainstormrouter.com/v1/memory/init \
  -H "Authorization: Bearer br_live_..." \
  -H "Content-Type: application/json" \
  -d '{ \
    "documents": [ \
      {"content": "Project uses Next.js 15 with App Router...", "source": "README.md"}, \
      {"content": "Deploy to AWS ECS Fargate via GitHub Actions...", "source": "infra.md"} \
    ], \
    "model": "anthropic/claude-sonnet-4" \
  }'
```

--------------------------------

### GET /v1/governance/agent-manifests

Source: https://brainstormrouter.com/llms-full.txt

Retrieves agent manifests. This endpoint allows you to fetch the details of agent manifests.

```APIDOC
## GET /v1/governance/agent-manifests

### Description
Retrieves a list of agent manifests.

### Method
GET

### Endpoint
/v1/governance/agent-manifests

### Parameters
#### Path Parameters
- **agentId** (string) - Required - The ID of the agent.

### Request Example
{
  "example": ""
}

### Response
#### Success Response (200)
- **manifests** (array) - An array of agent manifest objects.

#### Response Example
{
  "manifests": [
    {
      "agentId": "agent123",
      "name": "Agent Name",
      "description": "Agent Description"
    }
  ]
}
```