> ## Documentation Index
> Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# List Managed Policies
> Get all Managed Policies maintained by Requesty. Each entry is a policy whose `id` can be used directly as the `model` in a request, without the `policy/` prefix. No authentication is required and results are not scoped to an organization.
```bash cURL theme={"dark"}
curl https://router.requesty.ai/v1/models/managed
```
```python Python theme={"dark"}
import httpx
response = httpx.get("https://router.requesty.ai/v1/models/managed")
for policy in response.json()["data"]:
print(policy["id"])
```
```typescript TypeScript theme={"dark"}
const response = await fetch("https://router.requesty.ai/v1/models/managed");
const { data } = await response.json();
for (const policy of data) {
console.log(policy.id);
}
```
```json Response 200 theme={"dark"}
{
"object": "list",
"data": [
{
"api": "chat",
"id": "claude-sonnet-4-5",
"object": "model",
"created": 1770317868,
"owned_by": "system",
"input_price": 0.0000033,
"caching_price": 0.00000413,
"cached_price": 0.00000033,
"output_price": 0.0000165,
"pricing": [
{
"prompt_tokens_threshold": 0,
"input_price": 0.0000033,
"caching_price": 0.00000413,
"caching_5m_price": 0.00000413,
"caching_1h_price": 0.0000066,
"cached_price": 0.00000033,
"output_price": 0.0000165
}
],
"max_output_tokens": 64000,
"context_window": 1000000,
"supports_caching": true,
"supports_vision": true,
"supports_computer_use": true,
"supports_reasoning": true,
"supports_image_generation": false,
"supports_tool_calling": true,
"supports_role_developer": false,
"supports_web_search": true,
"supports_output_json_object": true,
"supports_output_json_schema": true,
"description": "Claude Sonnet 4.5 is Anthropic's balanced model for coding and agentic tasks.",
"data_retention": false,
"data_retention_days": 0,
"data_used_for_training": false,
"privacy_comments": "N/A",
"geolocation": "us"
},
{
"api": "chat",
"id": "gpt-5-mini@eu",
"object": "model",
"created": 1783669626,
"owned_by": "system",
"input_price": 0.00000025,
"cached_price": 0.000000025,
"output_price": 0.000002,
"max_output_tokens": 128000,
"context_window": 400000,
"supports_caching": true,
"supports_vision": true,
"supports_reasoning": true,
"supports_tool_calling": true,
"supports_output_json_object": true,
"supports_output_json_schema": true,
"description": "GPT-5 mini is a cost-efficient model for well-defined tasks.",
"data_retention": false,
"data_retention_days": 0,
"data_used_for_training": false,
"privacy_comments": "N/A",
"geolocation": "eu"
}
]
}
```
List the [Managed Policies](/features/managed-policies) that Requesty maintains. Each entry describes one policy: the `id` is the value you pass as `model` in a request (no `policy/` prefix), and the pricing and capability fields come from the models the policy routes across.
This endpoint requires no authentication and is not scoped to an organization — it returns every managed policy, including ones whose models are not on your organization's approved list. Policies suffixed with `@eu` route only through EU-hosted providers.
Use [`GET /v1/models`](/api-reference/endpoint/models-list) for the individual models and for your organization's own policies.
## OpenAPI
````yaml GET /v1/models/managed
openapi: 3.0.3
info:
title: Requesty Inference API
description: >-
Requesty Inference API for AI model routing. OpenAI-compatible endpoints for
chat completions, embeddings, images, audio, and more.
version: 1.0.0
servers:
- url: https://router.requesty.ai
description: Inference router endpoint
security:
- BearerAuth: []
paths:
/v1/models/managed:
servers:
- url: https://router.requesty.ai
description: Inference router endpoint
get:
summary: List managed policies
description: >-
Get all Managed Policies maintained by Requesty. Each entry is a policy
whose `id` can be used directly as the `model` in a request, without the
`policy/` prefix. No authentication is required and results are not
scoped to an organization.
operationId: listManagedPolicies
responses:
'200':
description: List of managed policies
content:
application/json:
schema:
$ref: '#/components/schemas/ModelsResponse'
example:
object: list
data:
- api: chat
id: claude-sonnet-4-5
object: model
created: 1770317868
owned_by: system
input_price: 0.0000033
cached_price: 3.3e-7
output_price: 0.0000165
max_output_tokens: 64000
context_window: 1000000
supports_caching: true
supports_vision: true
supports_reasoning: true
supports_tool_calling: true
geolocation: us
- api: chat
id: gpt-5-mini@eu
object: model
created: 1783669626
owned_by: system
input_price: 2.5e-7
cached_price: 2.5e-8
output_price: 0.000002
max_output_tokens: 128000
context_window: 400000
supports_caching: true
supports_vision: true
supports_reasoning: true
supports_tool_calling: true
geolocation: eu
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
security:
- {}
components:
schemas:
ModelsResponse:
type: object
required:
- object
- data
properties:
object:
type: string
enum:
- list
description: The object type, always 'list'
data:
type: array
items:
$ref: '#/components/schemas/Model'
description: The list of available models
ErrorResponse:
type: object
required:
- error
properties:
error:
type: object
required:
- origin
- message
properties:
origin:
type: string
enum:
- router
- provider
description: >-
Whether the error originated from Requesty's router or an
upstream provider.
message:
type: string
description: Human-readable error description.
Model:
type: object
properties:
api:
type: string
description: The modality of the model, e.g. 'chat'
id:
type: string
description: The model identifier (e.g., 'openai/gpt-5-mini')
object:
type: string
enum:
- model
description: The object type, always 'model'
created:
type: integer
description: The Unix timestamp (in seconds) when the model was created
owned_by:
type: string
description: The system or organization that owns the model
example: system
input_price:
type: number
format: float
description: Price per input token in USD
caching_price:
type: number
format: float
description: Price per token for caching in USD
cached_price:
type: number
format: float
description: Price per cached token in USD
output_price:
type: number
format: float
description: Price per output token in USD
pricing_scheme:
type: string
description: Pricing scheme hint when the model is not priced per token
pricing:
type: array
description: >-
Pricing bands, ordered by prompt token threshold. A band applies
once the prompt exceeds its `prompt_tokens_threshold`.
items:
$ref: '#/components/schemas/PricingBand'
max_output_tokens:
type: integer
description: Maximum number of output tokens the model can generate
context_window:
type: integer
description: Maximum context window size in tokens
supports_caching:
type: boolean
description: Whether the model supports caching
supports_vision:
type: boolean
description: Whether the model supports vision/image inputs
supports_computer_use:
type: boolean
description: Whether the model supports computer use capabilities
supports_reasoning:
type: boolean
description: Whether the model supports reasoning capabilities
supports_image_generation:
type: boolean
description: Whether the model can generate images
supports_tool_calling:
type: boolean
description: Whether the model supports tool/function calling
supports_role_developer:
type: boolean
description: Whether the model supports the `developer` message role
supports_web_search:
type: boolean
description: Whether the model supports web search via the `web_search` tool type
supports_output_json_object:
type: boolean
description: >-
Whether the model supports `response_format` with `{ "type":
"json_object" }`
supports_output_json_schema:
type: boolean
description: >-
Whether the model supports strict structured outputs via
`response_format` with `{ "type": "json_schema" }`
description:
type: string
description: A description of the model's capabilities and use cases
data_retention:
type: boolean
description: Whether the provider retains request data
data_retention_days:
type: integer
description: Number of days the provider retains request data
data_used_for_training:
type: boolean
description: Whether the provider may use request data for training
privacy_comments:
type: string
description: Additional privacy notes for the model
geolocation:
type: string
description: Region the model is served from, e.g. 'us' or 'eu'
retires_at:
type: string
format: date-time
description: >-
When the model is scheduled to be retired, in ISO 8601 format. After
this date, requests to the model fail. Null if no retirement is
scheduled.
PricingBand:
type: object
properties:
prompt_tokens_threshold:
type: integer
description: Prompt token count from which this band applies
input_price:
type: number
format: float
description: Price per input token in USD
caching_price:
type: number
format: float
description: Price per token for writing to the cache in USD
caching_5m_price:
type: number
format: float
description: Price per token for a 5 minute cache write in USD
caching_1h_price:
type: number
format: float
description: Price per token for a 1 hour cache write in USD
cached_price:
type: number
format: float
description: Price per cached input token in USD
output_price:
type: number
format: float
description: Price per output token in USD
pricing_scheme:
type: string
description: Pricing scheme hint for this band
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key for authentication
````