Crun Responses API

curl --request POST \
  --url https://api.crun.ai/api/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4",
  "instructions": "You are a concise product copywriter.",
  "input": "Write a one-sentence launch caption for a noise-canceling headset.",
  "temperature": 0.7
}
'

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1772294400,
  "status": "completed",
  "model": "gpt-5.4",
  "output": [
    {
      "id": "msg_abc123",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp."
        }
      ]
    }
  ],
  "output_text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp.",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 14,
    "total_tokens": 32
  }
}

POST

api

responses

curl --request POST \
  --url https://api.crun.ai/api/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4",
  "instructions": "You are a concise product copywriter.",
  "input": "Write a one-sentence launch caption for a noise-canceling headset.",
  "temperature": 0.7
}
'

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1772294400,
  "status": "completed",
  "model": "gpt-5.4",
  "output": [
    {
      "id": "msg_abc123",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp."
        }
      ]
    }
  ],
  "output_text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp.",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 14,
    "total_tokens": 32
  }
}

API Endpoint

POST https://api.crun.ai/api/v1/responses

The Responses API is OpenAI’s newer model interface for text and image inputs, text outputs, stateful follow-ups, structured outputs, and tool-using workflows. This endpoint follows the OpenAI Response request and response format. It is designed for direct use with the official OpenAI SDKs and other OpenAI-compatible clients.

Authentication

You can authenticate with either:

Authorization: Bearer YOUR_API_KEY
X-API-KEY: YOUR_API_KEY

When to Use Responses

Use /responses when you want:

Top-level instructions instead of a system message.
A flexible input field that can be a string or a list of message-like items.
Stateful follow-ups with previous_response_id when the upstream model supports stored responses.
Structured outputs through text.format.
Tool-ready response items and tools / tool_choice fields.

Use /chat/completions when you need the classic messages -> choices[] -> message shape for an existing chat integration.

Basic Text Generation

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "instructions": "You are a concise product copywriter.",
    "input": "Write a one-sentence launch caption for a noise-canceling headset.",
    "temperature": 0.7
  }'

Message-Style Input

The input field can also contain a list of message-like items, which makes migration from Chat Completions straightforward.

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Explain prompt caching in two short bullet points."
      }
    ]
  }'

Image Input

When the selected model supports vision, pass images in the content array with type: "input_image". You can use a public image URL, a Base64 data URL for vision.

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "Describe this image in one paragraph."
          },
          {
            "type": "input_image",
            "image_url": "https://example.com/product-photo.jpg"
          }
        ]
      }
    ]
  }'

File Input

For PDFs and other uploaded files supported by the upstream model, upload the file first and pass it as an input_file content part.

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "what is in this file?"
          },
          {
            "type": "input_file",
            "file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf"
          }
        ]
      }
    ]
  }'

Stateful Follow-Up

When the upstream model supports stored responses, set store=true and pass previous_response_id to continue from a previous response without resending all context.

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Give me three naming ideas for a developer newsletter.",
    "store": true
  }'

curl -X POST "https://api.crun.ai/api/v1/responses" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.4",
"input": "Make the names more playful.",
"previous_response_id": "resp_abc123",
"store": true
}'

Structured Output

For Responses, structured output uses text.format. This differs from Chat Completions, where the equivalent field is response_format.

curl -X POST "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Extract a task from: Maya should send the launch brief by Friday.",
    "text": {
      "format": {
        "type": "json_schema",
        "name": "task",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {
            "owner": { "type": "string" },
            "task": { "type": "string" },
            "due": { "type": "string" }
          },
          "required": ["owner", "task", "due"],
          "additionalProperties": false
        }
      }
    }
  }'

Tool-Ready Request

OpenAI’s Responses API supports built-in tools and function-style tools. CRUN accepts compatible tools and tool_choice fields and forwards them when the selected upstream model supports them.

tool request

{
  "model": "gpt-5.4",
  "input": "Search my connected knowledge base and summarize our refund policy.",
  "tools": [
    {
      "type": "file_search",
      "vector_store_ids": [
        "vs_123"
      ]
    }
  ],
  "tool_choice": "auto"
}

Streaming

Set stream=true to receive Server-Sent Events from /responses. Each event includes an event: line followed by a JSON data: payload.

curl -N "https://api.crun.ai/api/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "instructions": "You are a concise assistant.",
    "input": "Write a three-step checklist for reviewing an API integration.",
    "stream": true
  }'

Response Examples

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1772294400,
  "status": "completed",
  "model": "gpt-5.4",
  "output": [
    {
      "id": "msg_abc123",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp."
        }
      ]
    }
  ],
  "output_text": "Launch focus anywhere with a headset that quiets distractions and keeps calls crisp.",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 14,
    "total_tokens": 32
  }
}

Notes

max_output_tokens is capped by the selected model’s output token limit.
Additional OpenAI-compatible fields are accepted and passed through when supported by the upstream model.
Structured outputs use text.format; Chat Completions uses response_format.
Tool availability depends on the selected model and upstream provider.
Unknown model IDs return an OpenAI-style error body with code: "model_not_found".

LLM Quickstart

Learn the base URL, authentication method, and official SDK integration pattern.

Chat Completions API

Use the classic messages and choices API for existing chat clients.

Pricing

Jump to the pricing page to compare billing across different models.

Authorizations

Authorization

string

header

required

Use your CRUN API key as a Bearer token for OpenAI-compatible SDKs.

Body

application/json

OpenAI-compatible Responses request. Additional compatible fields are accepted and passed through when supported by the upstream model.

model

string

required

Public model ID returned by GET /api/v1/models.

Required string length: 1 - 128

Example:

"gpt-5.4"

input

Model input. Can be a string or a list of response input items; supports text, image, and file content parts depending on the selected model and upstream provider.

Example:

"Write a one-sentence launch caption for a noise-canceling headset."

instructions

System or developer instructions for the model.

Example:

"You are a concise product copywriter."

stream

boolean

default:false

Whether to return a Server-Sent Events stream.

Example:

false

store

boolean

Whether the upstream provider should store the response for stateful follow-ups, when supported.

Example:

true

previous_response_id

string

ID of a previous stored response to continue from, when supported.

Example:

"resp_abc123"

metadata

object

Developer-defined metadata.

max_output_tokens

integer

Maximum output tokens. Capped by the selected model.

Required range: x >= 1

Example:

512

temperature

number

Sampling temperature.

Required range: 0 <= x <= 2

Example:

0.7

top_p

number

Nucleus sampling value.

Required range: 0 <= x <= 1

Example:

1

user

string

End-user identifier passed for observability.

Example:

"user_123"

prompt_cache_key

string

Prompt cache key passed to the upstream provider when supported.

prompt_cache_retention

enum<string>

Prompt cache retention policy when supported.

Available options:

in-memory,

24h

reasoning

object

Reasoning model configuration.

Example:

{ "effort": "medium" }

text

object

Text output configuration. Use text.format for structured outputs in the Responses API.

Example:

{ "format": { "type": "json_object" } }

tools

object[]

Tool definitions in OpenAI-compatible Responses format.

tool_choice

Tool selection strategy.

Example:

"auto"

parallel_tool_calls

boolean

Whether to allow parallel tool calls when supported.

Example:

true

truncation

string

Context truncation strategy when supported.

Example:

"auto"

Response

Successful response. Returns JSON when stream=false, or SSE when stream=true.

string

Example:

"resp_abc123"

object

string

Example:

"response"

created_at

integer

Unix timestamp in seconds.

Example:

1772294400

status

string

Example:

"completed"

model

string

Public model ID requested by the client.

Example:

"gpt-5.4"

output

object[]

Show child attributes

output_text

string

Convenience text field when provided by the upstream provider.

Example:

"Launch focus anywhere with a headset that quiets distractions and keeps calls crisp."

usage

object

Show child attributes

LLM Quickstart Anthropic Messages

​API Endpoint

​Authentication

​When to Use Responses

​Basic Text Generation

​Message-Style Input

​Image Input

​File Input

​Stateful Follow-Up

​Structured Output

​Tool-Ready Request

​Streaming

​Response Examples

​Notes

​Related Resources

LLM Quickstart

Chat Completions API

Pricing

Authorizations

Body

Response

API Endpoint

Authentication

When to Use Responses

Basic Text Generation

Message-Style Input

Image Input

File Input

Stateful Follow-Up

Structured Output

Tool-Ready Request

Streaming

Response Examples

Notes

Related Resources