Requesty

https://docs.requesty.ai/
Admin
Requesty is a unified LLM gateway and OpenAI-compatible API that provides intelligent routing,...
Tokens:322,592
Snippets:2,205
Trust Score:8.3
Update:1 month ago
Show doc for...
Tokens:
Raw
### Quick start installation on macOS/Linux

Source: https://docs.requesty.ai/integrations/requesty-cli

Run this command to download and install the Requesty CLI. The installer places the binary in ~/.requesty/bin and adds it to your PATH.

```bash
curl -fsSL https://raw.githubusercontent.com/requestyai/cli/main/install.sh | sh
```

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

### EU Routing Quick Start Examples

Source: https://docs.requesty.ai/features/eu-routing

Code examples for using the EU routing endpoint with different SDKs and cURL.

```python
import openai

client = openai.OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.eu.requesty.ai/v1",  # EU endpoint
)

response = client.chat.completions.create(
    model="bedrock/claude-sonnet-4-5-v2@eu-central-1",  # EU model
    messages=[{"role": "user", "content": "Hello from Europe!"}]
)

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

```typescript
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'YOUR_REQUESTY_API_KEY',
    baseURL: 'https://router.eu.requesty.ai/v1',  // EU endpoint
});

const response = await client.chat.completions.create({
    model: 'bedrock/claude-sonnet-4-5-v2@eu-central-1',  // EU model
    messages: [{ role: 'user', content: 'Hello from Europe!' }],
});

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

```python
import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.eu.requesty.ai",  # EU endpoint (no /v1)
)

message = client.messages.create(
    model="bedrock/claude-sonnet-4-5-v2@eu-central-1",  # EU model
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello from Europe!"}]
)

print(message.content[0].text)
```

```bash
curl https://router.eu.requesty.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bedrock/claude-sonnet-4-5-v2@eu-central-1",
    "messages": [{"role": "user", "content": "Hello from Europe!"}]
  }'
```

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

### Install OpenAI SDK (Python)

Source: https://docs.requesty.ai/quickstart

Installs the openai Python package, which is required for the Python example.

```bash
pip install openai
```

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

### Install OpenAI SDK (TypeScript)

Source: https://docs.requesty.ai/quickstart

Installs the openai npm package, which is required for the TypeScript example.

```bash
npm install openai
```

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

### Basic Streaming Setup in Python

Source: https://docs.requesty.ai/features/streaming

Enable streaming by setting stream=True in the OpenAI client. The example uses the Requesty base URL and processes the response chunks, printing content as it arrives.

```python
import openai

client = openai.OpenAI(
    api_key="your_requesty_api_key",
    base_url="https://router.requesty.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-5.6-sol",
    messages=[{"role": "user", "content": "Write a poem about the stars."}],
    stream=True
)

# Process streaming response
for chunk in response:
    if chunk.choices[0].delta.content is not None:
        content = chunk.choices[0].delta.content
        print(content, end="", flush=True)
```

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

### Basic Streaming Setup in JavaScript

Source: https://docs.requesty.ai/features/streaming

Enable streaming by setting stream: true in the OpenAI client. The example uses the Requesty base URL and iterates over the stream, writing content to stdout.

```javascript
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_requesty_api_key',
  baseURL: 'https://router.requesty.ai/v1',
});

const stream = await openai.chat.completions.create({
  model: 'openai/gpt-5.6-sol',
  messages: [{ role: 'user', content: 'Write a poem about the stars.' }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    process.stdout.write(content);
  }
}
```

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

### Run OpenClaw onboarding wizard

Source: https://docs.requesty.ai/integrations/openclaw

Starts the OpenClaw onboarding wizard. Select Custom Provider and follow the prompts to configure Requesty.

```bash
openclaw onboard
```

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

### Open OpenCode in any project

Source: https://docs.requesty.ai/integrations/opencode

Navigate to your project directory and launch OpenCode to begin the /connect setup.

```bash
cd /path/to/project
opencode
```

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

### GET /v1/models/all

Source: https://docs.requesty.ai/api-reference/endpoint/models-all-list

Documentation for the GET /v1/models/all endpoint, including authentication behavior and response example.

```APIDOC
## GET /v1/models/all

### Description
Get all available models of every modality in a single list. Each entry is the same object the modality specific endpoint returns, identified by its `api` field. If authenticated with a Requesty API key, returns only the models approved for your organization. Otherwise, returns all public models.

### Method
GET

### Endpoint
https://router.requesty.ai/v1/models/all

### Authentication
Optional. Send the API key as either `Authorization: Bearer YOUR_REQUESTY_API_KEY` or `X-Api-Key: YOUR_REQUESTY_API_KEY`; both headers behave identically.

| Request                                  | Status | Result                                                                              |
| ---------------------------------------- | ------ | ----------------------------------------------------------------------------------- |
| No `Authorization` or `X-Api-Key` header | `200`  | All publicly available models                                                       |
| Valid API key                            | `200`  | Only the models approved for your organization and allowed by the key's access list |
| Invalid, expired or revoked API key      | `403`  | `Invalid authorization token` — the request is rejected, not treated as anonymous   |

### Response
#### Success Response (200)
Returns a list of available models. Each model object includes fields such as `api`, `id`, `object`, `created`, `updated`, `owned_by`, pricing information, `max_output_tokens`, `context_window`, and various capability flags.

#### Response Example
```json
{
  "object": "list",
  "data": [
    {
      "api": "chat",
      "id": "vertex/claude-sonnet-4-5",
      "object": "model",
      "created": 1747933971,
      "updated": 1747933971,
      "owned_by": "system",
      "input_price": 0.000003,
      "caching_price": 0.00000375,
      "cached_price": 3.e-7,
      "output_price": 0.000015,
      "pricing": [
        {
          "prompt_tokens_threshold": 0,
          "input_price": 0.000003,
          "caching_price": 0.00000375,
          "caching_5m_price": 0.00000375,
          "caching_1h_price": 0.000006,
          "cached_price": 3.e-7,
          "output_price": 0.000015
        },
        {
          "prompt_tokens_threshold": 200000,
          "input_price": 0.000006,
          "caching_price": 0.0000075,
          "caching_5m_price": 0.0000075,
          "caching_1h_price": 0.000012,
          "cached_price": 6.e-7,
          "output_price": 0.0000225
        }
      ],
      "max_output_tokens": 64000,
      "context_window": 200000,
      "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": "The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.",
      "data_retention": false,
      "data_retention_days": 0,
      "data_used_for_training": false,
      "privacy_comments": "N/A",
      "geolocation": "global",
      "open_weights": false,
      "model_lab": "vertex",
      "model_canonical_name": "tbd"
    },
    {
      "api": "embedding",
      "id": "vertex/google/gemini-embedding-2-preview",
      "object": "model",
      "created": 1774621394,
      "updated": 1774621394,
      "owned_by": "system",
      "pricing": {
        "input_text": 2.e-7,
        "input_audio": 0.0000064
      }
    }
  ]
}
```
```

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

### Run the /connect command

Source: https://docs.requesty.ai/integrations/opencode

Run /connect in OpenCode and select Requesty from the provider list to start the integration.

```txt
/connect
```

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

### Install DeepSeek Harness with npx

Source: https://docs.requesty.ai/integrations/deepseek-harness

Run the web UI once to create the harness home directory. This command initializes the harness environment.

```bash
npx @deepseek-ai/dsh web
```

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

### Framework Integration Examples

Source: https://docs.requesty.ai/features/structured-outputs

Code examples showing how to use structured outputs with LangChain, Instructor, Pydantic AI, LiteLLM, and DSPy frameworks, all pointing to Requesty's OpenAI-compatible endpoint.

```python
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage, HumanMessage
from pydantic import BaseModel

class Answer(BaseModel):
    championships: int
    summary: str

llm = ChatOpenAI(
    model="anthropic/claude-sonnet-4-5",
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

# .with_structured_output() sends json_schema under the hood
structured_llm = llm.with_structured_output(Answer)

result = structured_llm.invoke([
    SystemMessage(content="Answer questions about NBA players."),
    HumanMessage(content="How many championships has LeBron James won?"),
])
print(f"{result.championships} championships")
```

```python
import instructor
from openai import OpenAI
from pydantic import BaseModel

client = instructor.from_openai(OpenAI())

class UserInfo(BaseModel):
    name: str
    age: int
    email: str

user = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    response_model=UserInfo,
    messages=[
        {"role": "user", "content": "John is 30 years old. His email is john@example.com"},
    ],
)
print(f"{user.name}, {user.age}, {user.email}")
```

```python
from pydantic_ai import Agent, OpenAIProvider
from pydantic import BaseModel

class CityInfo(BaseModel):
    name: str
    country: str
    population: int
    known_for: list[str]

provider = OpenAIProvider(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

agent = Agent(
    model="anthropic/claude-sonnet-4-5",
    system_prompt="Provide information about cities.",
    output_type=CityInfo,
)

result = agent.run_sync("Tell me about Tokyo")
print(f"{result.output.name}, {result.output.country}")
print(f"Known for: {', '.join(result.output.known_for)}")
```

```python
import litellm
import json

response = litellm.completion(
    model="openai/anthropic/claude-sonnet-4-5",
    messages=[
        {"role": "system", "content": "Extract the key entities."},
        {"role": "user", "content": "Apple Inc. was founded by Steve Jobs in Cupertino."},
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "Entities",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {
                    "companies": {"type": "array", "items": {"type": "string"}},
                    "people": {"type": "array", "items": {"type": "string"}},
                    "locations": {"type": "array", "items": {"type": "string"}}
                },
                "required": ["companies", "people", "locations"],
                "additionalProperties": False
            }
        }
    },
    api_key="YOUR_REQUESTY_API_KEY",
    api_base="https://router.requesty.ai/v1",
)

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

```python
import dspy

class ExtractInfo(dspy.Signature):
    """Extract structured information from text."""
    text: str = dspy.InputField()
    companies: list[str] = dspy.OutputField(desc="Company names mentioned")
    people: list[str] = dspy.OutputField(desc="People mentioned")
    locations: list[str] = dspy.OutputField(desc="Locations mentioned")

lm = dspy.LM(
    model="openai/anthropic/claude-sonnet-4-5",
    api_key="YOUR_REQUESTY_API_KEY",
    api_base="https://router.requesty.ai/v1",
)

with dspy.context(lm=lm):
    predict = dspy.Predict(ExtractInfo)
    result = predict(text="Sundar Pichai leads Google from their Mountain View office.")
    print(result.companies)  # ["Google"]
    print(result.people)     # ["Sundar Pichai"]
```

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

### OpenAPI Specification for GET /v1/models/all

Source: https://docs.requesty.ai/api-reference/endpoint/models-all-list

OpenAPI specification for the GET /v1/models/all endpoint, showing the request and response schema with example model data.

```yaml
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/all:
    servers:
      - url: https://router.requesty.ai
        description: Inference router endpoint
    get:
      summary: List available models across all modalities
      description: >-
        Get all available models of every modality in a single list. Each entry
        is the same object the modality specific endpoint returns, identified by
        its `api` field. If authenticated with a Requesty API key, returns only
        the models approved for your organization. Otherwise, returns all public
        models.
      operationId: listAllModels
      responses:
        '200':
          description: List of available models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AllModelsResponse'
              example:
                object: list
                data:
                  - api: chat
                    id: vertex/claude-sonnet-4-5
                    object: model
                    created: 1747933971
                    updated: 1747933971
                    owned_by: system
                    input_price: 0.000003
                    caching_price: 0.00000375
                    cached_price: 3.e-7
                    output_price: 0.000015
                    pricing:
                      - prompt_tokens_threshold: 0
                        input_price: 0.000003
                        caching_price: 0.00000375
                        caching_5m_price: 0.00000375
                        caching_1h_price: 0.000006
                        cached_price: 3.e-7
                        output_price: 0.000015
                      - prompt_tokens_threshold: 200000
                        input_price: 0.000006
                        caching_price: 0.00000375
                        caching_5m_price: 0.00000375
                        caching_1h_price: 0.000006
                        cached_price: 6.e-7
                        output_price: 0.0000225
                    max_output_tokens: 64000
                    context_window: 200000
                    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: >-
                      The first hybrid reasoning model on the market with the
                      highest level of intelligence and capability with
                      toggleable extended thinking. Top-tier results in
                      reasoning, coding, multilingual tasks, long-context
                      handling, honesty, and image processing.
                    data_retention: false
                    data_retention_days: 0
                    data_used_for_training: false
                    privacy_comments: N/A
                    geolocation: global
                    open_weights: false
                    model_lab: vertex
                    model_canonical_name: tbd
                  - api: embedding
                    id: vertex/google/gemini-embedding-2-preview
                    object: model
                    created: 1774621394
                    updated: 1774621394
                    owned_by: system
                    pricing:
                      input_text: 2.e-7
                      input_audio: 0.0000064
```

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

### Model Configuration and Verification Prompt

Source: https://docs.requesty.ai/integrations/opencode

Configuration example for setting the default model in OpenCode, and a sample prompt to verify the integration.

```json
{
  "model": "requesty/openai/gpt-5"
}
```

```txt
> Summarize the README of this repo in 3 bullet points.
```

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

### cURL Request to Get Organization Usage

Source: https://docs.requesty.ai/api-reference/endpoint/manage-org-get-usage

Sends a GET request to /v1/manage/org/usage with start, end, resolution, and group_by parameters. Requires a Bearer token for authentication.

```bash
curl -X GET "https://api-v2.requesty.ai/v1/manage/org/usage?start=2025-01-01T00:00:00Z&end=2025-01-31T23:59:59Z&resolution=day&group_by=model_used" \
  -H "Authorization: Bearer YOUR_API_KEY"
```

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

### Example 200 response for /v1/models/chat

Source: https://docs.requesty.ai/api-reference/endpoint/models-chat-list

Example 200 response from the /v1/models/chat endpoint. Shows a model object with pricing tiers, capability flags, and metadata. The response is identical to GET /v1/models.

```json
{
  "object": "list",
  "data": [
    {
      "api": "chat",
      "id": "vertex/claude-sonnet-4-5",
      "object": "model",
      "created": 1747933971,
      "updated": 1747933971,
      "owned_by": "system",
      "pricing": [
        {
          "prompt_tokens_threshold": 0,
          "input_price": 3e-06,
          "caching_price": 3.75e-06,
          "caching_5m_price": 3.75e-06,
          "caching_1h_price": 6e-06,
          "cached_price": 3e-07,
          "output_price": 1.5e-05
        },
        {
          "prompt_tokens_threshold": 200000,
          "input_price": 6e-06,
          "caching_price": 7.5e-06,
          "caching_5m_price": 7.5e-06,
          "caching_1h_price": 1.2e-05,
          "cached_price": 6e-07,
          "output_price": 2.25e-05
        }
      ],
      "max_output_tokens": 64000,
      "context_window": 200000,
      "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": "The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.",
      "data_retention": false,
      "data_retention_days": 0,
      "data_used_for_training": false,
      "privacy_comments": "N/A",
      "geolocation": "global",
      "open_weights": false,
      "model_lab": "vertex",
      "model_canonical_name": "claude-sonnet-4-5"
    }
  ]
}
```

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

### Use descriptions for guidance

Source: https://docs.requesty.ai/features/structured-outputs

Example of adding a description field to a schema property to guide the model.

```json
{
  "type": "object",
  "properties": {
    "confidence": {
      "type": "number",
      "description": "A confidence score between 0.0 and 1.0"
    }
  }
}
```

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

### Instructions Parameter

Source: https://docs.requesty.ai/api-reference/endpoint/responses-create

Example of using the instructions parameter to set a system-level prompt.

```json
{
	"model": "openai-responses/gpt-5",
	"instructions": "You are a helpful assistant that always responds in JSON.",
	"input": "Summarize the weather in Paris today."
}
```

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

### OpenAPI Specification for GET /v1/manage/org/usage

Source: https://docs.requesty.ai/api-reference/endpoint/manage-org-get-usage

Defines the GET /v1/manage/org/usage endpoint with parameters start, end, resolution, and group_by. The date range cannot exceed 100 days. The response schema references GetOrgUsageResponse and ErrorResponse.

```yaml
openapi: 3.0.3
info:
  title: Requesty API
  description: Requesty API for AI model routing and key management
  version: 1.0.0
servers:
  - url: https://api-v2.requesty.ai
    description: Management API endpoint
  - url: https://router.requesty.ai
    description: Inference router endpoint
security:
  - BearerAuth: []
paths:
  /v1/manage/org/usage:
    servers:
      - url: https://api-v2.requesty.ai
        description: Management API endpoint
    get:
      summary: Get organization usage
      description: >-
        Get aggregated usage statistics for your entire organization within a
        date range. Supports aggregation by different time periods and optional
        grouping by user, model, or custom fields.
      operationId: getOrgUsage
      parameters:
        - name: start
          in: query
          required: true
          schema:
            type: string
            format: date-time
            example: '2025-01-01T00:00:00Z'
          description: >-
            Start date in RFC3339 format (e.g., 2025-01-01T00:00:00Z). Required.
            The date range cannot exceed 100 days from start to end.
        - name: end
          in: query
          required: false
          schema:
            type: string
            format: date-time
            example: '2025-01-31T23:59:59Z'
          description: >-
            End date in RFC3339 format (e.g., 2025-01-31T23:59:59Z). Optional.
            Defaults to 24 hours from start if not specified. Must be after
            start date. The date range cannot exceed 100 days.
        - name: resolution
          in: query
          required: false
          schema:
            type: string
            enum:
              - hour
              - day
              - month
            default: day
          description: Time resolution for aggregation
        - name: group_by
          in: query
          required: false
          schema:
            type: array
            items:
              type: string
          description: >-
            Fields to group by: group_name, group_id, member_id, member_email,
            user_id, api_key_id, model_requested, model_used, provider_used,
            is_byok, origin_title, extra.<field_name>,
            api_key_label.<label_key>, or group_label.<label_key>. Rows missing
            a requested label are grouped under "Unknown". Can be specified
            multiple times.
      responses:
        '200':
          description: Successfully retrieved usage data
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetOrgUsageResponse'
        '400':
          description: Bad request - malformed payload or invalid parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized - missing or empty Authorization header.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '402':
          description: Payment required - organization balance exhausted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Forbidden - invalid token or model not in access list.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Not found - provider/model not supported.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Too many requests - rate limit exceeded.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
        - BearerAuth: []
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
  schemas:
    GetOrgUsageResponse:
      type: object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/UsageRecord'
        meta:
          type: object
          properties:
            start:
              type: string
              format: date-time
            end:
              type: string
              format: date-time
            resolution:
              type: string
              enum: [hour, day, month]
            group_by:
              type: array
              items:
                type: string
    UsageRecord:
      type: object
      properties:
        start:
          type: string
          format: date-time
        end:
          type: string
          format: date-time
        group_name:
          type: string
        group_id:
          type: string
        member_id:
          type: string
        member_email:
          type: string
        user_id:
          type: string
        api_key_id:
          type: string
        model_requested:
          type: string
        model_used:
          type: string
        provider_used:
          type: string
        is_byok:
          type: boolean
        origin_title:
          type: string
        extra:
          type: object
          additionalProperties:
            type: string
        api_key_labels:
          type: object
          additionalProperties:
            type: string
        group_labels:
          type: object
          additionalProperties:
            type: string
        total_requests:
          type: integer
        total_prompt_tokens:
          type: integer
        total_completion_tokens:
          type: integer
        total_tokens:
          type: integer
        total_cost_usd:
          type: number
        total_latency_ms:
          type: number
    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
            message:
              type: string
            details:
              type: object
              additionalProperties: true
```

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

### Install Requesty OpenCode wrapper

Source: https://docs.requesty.ai/integrations/opencode

Command to install the Requesty OpenCode wrapper.

```bash
curl -fsSL https://www.requesty.ai/opencode/install.sh | bash
```

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

### OpenAPI Specification for GET /v1/models/chat

Source: https://docs.requesty.ai/api-reference/endpoint/models-chat-list

YAML OpenAPI 3.0.3 specification for the GET /v1/models/chat endpoint. It defines the server URL, security scheme, and response schemas including a detailed example model object with pricing tiers and capabilities.

```yaml
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/chat:
    servers:
      - url: https://router.requesty.ai
        description: Inference router endpoint
    get:
      summary: List available chat models
      description: >-
        Get all available chat models. Identical to `GET /v1/models`, including
        your aliases and routing policies. If authenticated with a Requesty API
        key, returns only the models approved for your organization. Otherwise,
        returns all public models.
      operationId: listChatModels
      responses:
        '200':
          description: List of available models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelsResponse'
              example:
                object: list
                data:
                  - api: chat
                    id: vertex/claude-sonnet-4-5
                    object: model
                    created: 1747933971
                    updated: 1747933971
                    owned_by: system
                    input_price: 0.000003
                    caching_price: 0.00000375
                    cached_price: 3.e-7
                    output_price: 0.000015
                    pricing:
                      - prompt_tokens_threshold: 0
                        input_price: 0.000003
                        caching_price: 0.00000375
                        caching_5m_price: 0.00000375
                        caching_1h_price: 0.000006
                        cached_price: 3.e-7
                        output_price: 0.000015
                      - prompt_tokens_threshold: 200000
                        input_price: 0.000006
                        caching_price: 0.0000075
                        caching_5m_price: 0.0000075
                        caching_1h_price: 0.000012
                        cached_price: 6.e-7
                        output_price: 0.0000225
                    max_output_tokens: 64000
                    context_window: 200000
                    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: >-
                      The first hybrid reasoning model on the market with the
                      highest level of intelligence and capability with
                      toggleable extended thinking. Top-tier results in
                      reasoning, coding, multilingual tasks, long-context
                      handling, honesty, and image processing.
                    data_retention: false
                    data_retention_days: 0
                    data_used_for_training: false
                    privacy_comments: N/A
                    geolocation: global
                    open_weights: false
                    model_lab: vertex
                    model_canonical_name: tbd
        '400':
          description: Bad request - malformed payload or invalid parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized - missing or empty Authorization header.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '402':
```

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

### Example Request

Source: https://docs.requesty.ai/api-reference/endpoint/audio-speech-create

Example curl command to synthesize speech and save the audio to a file.

```bash
curl https://router.requesty.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  --output speech.mp3 \
  -d '{
    "model": "openai/gpt-4o-mini-tts",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy",
    "response_format": "mp3"
  }'
```

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

### Haystack Integration with Structured Outputs

Source: https://docs.requesty.ai/features/structured-outputs

Example of using Haystack's OpenAIChatGenerator with Requesty to get structured JSON output.

```python
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.utils import Secret
from haystack.dataclasses import ChatMessage
import json

generator = OpenAIChatGenerator(
    model="vertex/gemini-2.5-flash",
    api_key=Secret.from_token("YOUR_REQUESTY_API_KEY"),
    api_base_url="https://router.requesty.ai/v1",
    generation_kwargs={
        "response_format": {
            "type": "json_schema",
            "json_schema": {
                "name": "Analysis",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "topic": {"type": "string"},
                        "sentiment": {"type": "string"},
                        "confidence": {"type": "number"}
                    },
                    "required": ["topic", "sentiment", "confidence"],
                    "additionalProperties": False
                }
            }
        }
    },
)

generator.warm_up()
result = generator.run(messages=[
    ChatMessage.from_system("Analyze the topic and sentiment of the text."),
    ChatMessage.from_user("I absolutely love the new Python 3.13 release!"),
])

analysis = json.loads(result["replies"][0].text)
print(f"Topic: {analysis['topic']}, Sentiment: {analysis['sentiment']}")
```

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

### Example Response for Get Organization Usage

Source: https://docs.requesty.ai/api-reference/endpoint/manage-org-get-usage

Shows a successful response with usage records grouped by model_used. Each record includes token counts, cost, and latency.

```json
{
  "data": [
    {
      "start": "2025-01-01T00:00:00Z",
      "end": "2025-01-01T23:59:59Z",
      "model_used": "gpt-4o",
      "total_requests": 120,
      "total_prompt_tokens": 15000,
      "total_completion_tokens": 3000,
      "total_tokens": 18000,
      "total_cost_usd": 0.45,
      "total_latency_ms": 850
    },
    {
      "start": "2025-01-01T00:00:00Z",
      "end": "2025-01-01T23:59:59Z",
      "model_used": "claude-3-5-sonnet",
      "total_requests": 80,
      "total_prompt_tokens": 10000,
      "total_completion_tokens": 2000,
      "total_tokens": 12000,
      "total_cost_usd": 0.30,
      "total_latency_ms": 720
    }
  ],
  "meta": {
    "start": "2025-01-01T00:00:00Z",
    "end": "2025-01-31T23:59:59Z",
    "resolution": "day",
    "group_by": ["model_used"]
  }
}
```
Tokens:
Raw