Crun Chat Completions API

curl --request POST \
  --url https://api.crun.ai/api/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Write a short tagline for a coffee brand."
    }
  ],
  "temperature": 0.7
}
'

{
  "id": "chatcmpl_abc123",
  "object": "chat.completion",
  "created": 1772294400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Bright flavor, smooth finish, and roasted for everyday focus."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 13,
    "total_tokens": 31
  }
}

{
  "error": {
    "message": "Invalid JSON body",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

{
  "error": {
    "message": "API key missing",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "Insufficient Credits",
    "type": "insufficient_quota",
    "param": null,
    "code": "insufficient_credits"
  }
}

{
  "error": {
    "message": "The model `unknown-model` does not exist.",
    "type": "invalid_request_error",
    "param": null,
    "code": "model_not_found"
  }
}

{
  "error": {
    "message": "Field `messages` is required.",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

{
  "error": {
    "message": "Rate limit reached for this account, please retry later.",
    "type": "rate_limit_error",
    "param": null,
    "code": "rate_limit_exceeded"
  }
}

{
  "error": {
    "message": "Upstream request failed",
    "type": "api_error",
    "param": null,
    "code": null
  }
}

POST

api

chat

completions

curl --request POST \
  --url https://api.crun.ai/api/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Write a short tagline for a coffee brand."
    }
  ],
  "temperature": 0.7
}
'

{
  "id": "chatcmpl_abc123",
  "object": "chat.completion",
  "created": 1772294400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Bright flavor, smooth finish, and roasted for everyday focus."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 13,
    "total_tokens": 31
  }
}

{
  "error": {
    "message": "Invalid JSON body",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

{
  "error": {
    "message": "API key missing",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "Insufficient Credits",
    "type": "insufficient_quota",
    "param": null,
    "code": "insufficient_credits"
  }
}

{
  "error": {
    "message": "The model `unknown-model` does not exist.",
    "type": "invalid_request_error",
    "param": null,
    "code": "model_not_found"
  }
}

{
  "error": {
    "message": "Field `messages` is required.",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

{
  "error": {
    "message": "Rate limit reached for this account, please retry later.",
    "type": "rate_limit_error",
    "param": null,
    "code": "rate_limit_exceeded"
  }
}

{
  "error": {
    "message": "Upstream request failed",
    "type": "api_error",
    "param": null,
    "code": null
  }
}

API Endpoint

POST https://api.crun.ai/api/v1/chat/completions

This endpoint follows the OpenAI Chat Completions 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

Request Examples

curl -X POST "https://api.crun.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Summarize the benefits of serverless functions in 3 bullet points."
      }
    ],
    "temperature": 0.6
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.crun.ai/api/v1",
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Summarize the benefits of serverless functions in 3 bullet points."},
    ],
    temperature=0.6,
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.crun.ai/api/v1"
});

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Summarize the benefits of serverless functions in 3 bullet points." }
  ],
  temperature: 0.6
});

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

Conversation History Example

CRUN does not manage multi-turn conversation context for your application. To continue a conversation, you must manage prior message history yourself and include the relevant history in each new request.

curl -X POST "https://api.crun.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful support assistant."
      },
      {
        "role": "user",
        "content": "My package has not arrived yet. What should I check first?"
      },
      {
        "role": "assistant",
        "content": "First, check the tracking link, delivery address, and any carrier delay notices."
      },
      {
        "role": "user",
        "content": "The tracking page says delayed by weather. Draft a short reply to the customer."
      }
    ],
    "temperature": 0.6
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.crun.ai/api/v1",
)

messages = [
    {"role": "system", "content": "You are a helpful support assistant."},
    {"role": "user", "content": "My package has not arrived yet. What should I check first?"},
    {"role": "assistant", "content": "First, check the tracking link, delivery address, and any carrier delay notices."},
    {"role": "user", "content": "The tracking page says delayed by weather. Draft a short reply to the customer."},
]

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=messages,
    temperature=0.6,
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.crun.ai/api/v1"
});

const messages = [
  { role: "system", content: "You are a helpful support assistant." },
  { role: "user", content: "My package has not arrived yet. What should I check first?" },
  { role: "assistant", content: "First, check the tracking link, delivery address, and any carrier delay notices." },
  { role: "user", content: "The tracking page says delayed by weather. Draft a short reply to the customer." }
];

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages,
  temperature: 0.6
});

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

Structured Output Example

Use response_format when you need the model to return JSON. For schema-enforced structured outputs, use a model and upstream provider that support json_schema.

curl -X POST "https://api.crun.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {
        "role": "system",
        "content": "Extract tasks as JSON only."
      },
      {
        "role": "user",
        "content": "Maya should send the launch brief by Friday."
      }
    ],
    "response_format": {
      "type": "json_schema",
      "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
        }
      }
    }
  }'

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "system", "content": "Extract tasks as JSON only."},
        {"role": "user", "content": "Maya should send the launch brief by Friday."},
    ],
    response_format={
        "type": "json_schema",
        "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,
            },
        },
    },
)

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

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [
    { role: "system", content: "Extract tasks as JSON only." },
    { role: "user", content: "Maya should send the launch brief by Friday." }
  ],
  response_format: {
    type: "json_schema",
    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
      }
    }
  }
});

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

Tool Calling Example

Chat Completions accepts OpenAI-compatible tools and tool_choice fields. Your application is responsible for executing tool calls and sending tool results back in a follow-up request.

request body

{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather like in Paris?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a city.",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string"
            }
          },
          "required": ["city"],
          "additionalProperties": false
        }
      }
    }
  ],
  "tool_choice": "auto"
}

Vision Input Example

When the selected model supports image input, pass multimodal content parts in the user message.

request body

{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe this chart in one paragraph."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/chart.png"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 300
}

Streaming Example

Set stream=true to receive Server-Sent Events. CRUN enables usage reporting for streaming requests when possible.

curl -N "https://api.crun.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "stream": true,
    "messages": [
      {
        "role": "user",
        "content": "Write a three-step checklist for reviewing an API integration."
      }
    ],
    "stream_options": {
      "include_usage": true
    }
  }'

stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "user", "content": "Write a three-step checklist for reviewing an API integration."}
    ],
    stream=True,
    stream_options={"include_usage": True},
)

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

const stream = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [
    { role: "user", content: "Write a three-step checklist for reviewing an API integration." }
  ],
  stream: true,
  stream_options: { include_usage: true }
});

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

Response Examples

{
  "id": "chatcmpl_abc123",
  "object": "chat.completion",
  "created": 1772294400,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "- No server management.\n- Automatic scaling for bursty traffic.\n- Pay only for actual execution time."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 22,
    "completion_tokens": 19,
    "total_tokens": 41
  }
}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1772294400,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"- No server management."},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1772294400,"model":"gpt-5.4","choices":[{"index":0,"delta":{"content":"\\n- Automatic scaling for bursty traffic."},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1772294400,"model":"gpt-5.4","choices":[],"usage":{"prompt_tokens":22,"completion_tokens":19,"total_tokens":41}}

data: [DONE]

Notes

Set stream=true to receive a text/event-stream response.
If you omit stream_options.include_usage, CRUN enables it automatically for streaming requests.
max_tokens and max_completion_tokens are both accepted and are capped by the selected model’s output token limit.
Unknown model IDs return an OpenAI-style error body with code: "model_not_found".
For new stateful, tool-heavy, or structured-output workflows, also consider the /responses endpoint. Responses uses input, instructions, and text.format instead of messages and response_format.

Responses API

Build with flexible input, stateful follow-ups, structured outputs, and tool-ready response items.

LLM Quickstart

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

Models Overview

Explore all available image, video, audio, and language model APIs.

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 Chat Completions 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-4o-mini"

messages

object[]

required

Conversation messages in OpenAI format.

Minimum array length: 1

Show child attributes

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

integer

default:1

Number of completion choices to generate.

Required range: 1 <= x <= 8

Example:

1

stream

boolean

default:false

Whether to return a Server-Sent Events stream.

Example:

false

stop

Stop sequence or list of stop sequences.

Example:

"###"

max_tokens

integer

Maximum output tokens. Capped by the selected model.

Required range: x >= 1

Example:

512

max_completion_tokens

integer

Maximum completion tokens. Capped by the selected model.

Required range: x >= 1

Example:

512

presence_penalty

number

Presence penalty value.

Required range: -2 <= x <= 2

Example:

0

frequency_penalty

number

Frequency penalty value.

Required range: -2 <= x <= 2

Example:

0

user

string

End-user identifier passed for observability.

Example:

"user_123"

stream_options

object

Streaming options. When stream=true, CRUN enables include_usage=true by default if omitted.

Example:

{ "include_usage": true }

response_format

object

Structured output option in OpenAI-compatible format. Chat Completions uses response_format; Responses uses text.format.

Example:

{ "type": "json_object" }

tools

object[]

Tool definitions in OpenAI-compatible format. Your application executes tool calls and returns tool results in a follow-up request.

tool_choice

Tool selection strategy.

Example:

"auto"

Response

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

string

required

Example:

"chatcmpl_abc123"

object

string

required

Example:

"chat.completion"

created

integer

required

Unix timestamp in seconds.

Example:

1772294400

model

string

required

Public model ID requested by the client.

Example:

"gpt-4o-mini"

choices

object[]

required

Show child attributes

usage

object

Show child attributes

Anthropic Messages Nano Banana 2

Introduction

Language Models

Image Models

Video Models

Audio Models

Task

Crun Chat Completions API

API Endpoint

Authentication

Request Examples

Conversation History Example

Structured Output Example

Tool Calling Example

Vision Input Example

Streaming Example

Response Examples

Notes

Responses API

LLM Quickstart

Models Overview

Pricing

Authorizations

Body

Response

​API Endpoint

​Authentication

​Request Examples

​Conversation History Example

​Structured Output Example

​Tool Calling Example

​Vision Input Example

​Streaming Example

​Response Examples

​Notes

​Related Resources

Responses API

LLM Quickstart

Models Overview

Pricing

Authorizations

Body

Response

API Endpoint

Authentication

Request Examples

Conversation History Example

Structured Output Example

Tool Calling Example

Vision Input Example

Streaming Example

Response Examples

Notes

Related Resources