> ## Documentation Index
> Fetch the complete documentation index at: https://docs.crun.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Compatible LLM

> Connect CRUN language models through OpenAI-compatible endpoints and reuse the official OpenAI SDK.

## Overview

CRUN provides an OpenAI-compatible language model gateway under `https://api.crun.ai/api/v1`.
You can keep using the official OpenAI SDKs, Anthropic SDKs, or any client already compatible with OpenAI-style chat APIs, by only changing the base URL and API key.

<Info>
  Supported compatibility endpoints:

  * `GET /models`: list currently available public model IDs
  * `POST /responses`: OpenAI's latest API, recommended endpoint for new stateful, multimodal, and tool-using LLM workflows
  * `POST /messages`: Anthropic-compatible endpoint for Claude-style message clients
  * `POST /chat/completions`: OpenAI-compatible chat generation endpoint for existing chat clients
  * `POST /completions`: legacy text completions endpoint, without stream support in this compatibility layer
</Info>

## Base URL

```text theme={null}
https://api.crun.ai/api/v1
```

## Authentication

You can authenticate in either of these ways:

* `Authorization: Bearer YOUR_API_KEY`
* `X-API-KEY: YOUR_API_KEY`

For official OpenAI SDKs, we recommend using `Authorization: Bearer YOUR_API_KEY`.

<Warning>
  Keep your API key secure. Never expose it in client-side code or public repositories.
</Warning>

## Step 1: List Available Models

The exact model catalog may change over time. Always call `/models` to retrieve the latest public model IDs before integrating or switching models.

<CodeGroup>
  ```bash cURL theme={null} theme={null}
  curl -X GET "https://api.crun.ai/api/v1/models" \
    -H "Authorization: Bearer YOUR_API_KEY"
  ```

  ```python Python theme={null} theme={null}
  import requests

  response = requests.get(
      "https://api.crun.ai/api/v1/models",
      headers={"Authorization": "Bearer YOUR_API_KEY"},
      timeout=30,
  )

  print(response.json())
  ```

  ```javascript Node.js theme={null} theme={null}
  const response = await fetch("https://api.crun.ai/api/v1/models", {
    headers: {
      Authorization: "Bearer YOUR_API_KEY"
    }
  });

  console.log(await response.json());
  ```
</CodeGroup>

### Example Response

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.4",
      "object": "model",
      "created": 1772294400,
      "owned_by": "OpenAI"
    },
    {
      "id": "claude-sonnet-4-5",
      "object": "model",
      "created": 1772294400,
      "owned_by": "Anthropic"
    },
    {
      "id": "gemini-3.1-pro-preview",
      "object": "model",
      "created": 1772294400,
      "owned_by": "Google"
    }
  ]
}
```

## Step 2: Make Your First Chat Completion

Use `/chat/completions` when you already have an OpenAI Chat Completions client or want the classic `messages` and `choices` response shape. It follows the OpenAI Chat Completions request and response structure, so existing SDK integrations usually only need a base URL change.

<CodeGroup>
  ```bash cURL theme={null} theme={null}
  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 concise assistant."
        },
        {
          "role": "user",
          "content": "Write a two-line product description for a wireless keyboard."
        }
      ],
      "temperature": 0.7
    }'
  ```

  ```python Python (OpenAI SDK) theme={null} theme={null}
  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 concise assistant."},
          {"role": "user", "content": "Write a two-line product description for a wireless keyboard."},
      ],
      temperature=0.7,
  )

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

  ```javascript JavaScript (OpenAI SDK) theme={null} theme={null}
  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 concise assistant." },
      { role: "user", content: "Write a two-line product description for a wireless keyboard." }
    ],
    temperature: 0.7
  });

  console.log(response.choices[0].message.content);
  ```
</CodeGroup>

### Example Response

```json theme={null}
{
  "id": "chatcmpl_abc123",
  "object": "chat.completion",
  "created": 1772294400,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Slim, quiet, and built for all-day comfort.\nA reliable wireless keyboard for focused work at home or on the go."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 21,
    "total_tokens": 45
  }
}
```

## Step 3: Use the Responses API

Use `/responses` for new integrations that benefit from OpenAI's newer Responses shape: top-level `instructions`, flexible `input`, `previous_response_id` for stateful follow-ups, `text.format` for structured outputs, and `tools` when supported by the selected upstream model.

<CodeGroup>
  ```bash cURL theme={null} theme={null}
  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 assistant.",
      "input": "Write a two-line product description for a wireless keyboard.",
      "temperature": 0.7
    }'
  ```

  ```python Python (OpenAI SDK) theme={null} theme={null}
  from openai import OpenAI

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

  response = client.responses.create(
      model="gpt-5.4",
      instructions="You are a concise assistant.",
      input="Write a two-line product description for a wireless keyboard.",
      temperature=0.7,
  )

  print(response.output_text)
  ```

  ```javascript JavaScript (OpenAI SDK) theme={null} theme={null}
  import OpenAI from "openai";

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

  const response = await client.responses.create({
    model: "gpt-5.4",
    instructions: "You are a concise assistant.",
    input: "Write a two-line product description for a wireless keyboard.",
    temperature: 0.7
  });

  console.log(response.output_text);
  ```
</CodeGroup>

### Example Response

```json theme={null}
{
  "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": "Slim, quiet, and built for all-day comfort.\nA reliable wireless keyboard for focused work at home or on the go."
        }
      ]
    }
  ],
  "output_text": "Slim, quiet, and built for all-day comfort.\nA reliable wireless keyboard for focused work at home or on the go.",
  "usage": {
    "input_tokens": 20,
    "output_tokens": 21,
    "total_tokens": 41
  }
}
```

## Managing Conversation History

CRUN does not store or manage conversation state for you.
If you want the model to remember previous turns, your application must keep the relevant message history and send it again in each new `/chat/completions` request.

<CodeGroup>
  ```bash cURL theme={null} theme={null}
  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 concise travel assistant."
        },
        {
          "role": "user",
          "content": "I will spend 2 days in Tokyo. Build a simple itinerary."
        },
        {
          "role": "assistant",
          "content": "Day 1: Asakusa and Ueno. Day 2: Shibuya and Meiji Shrine."
        },
        {
          "role": "user",
          "content": "Update it for rainy weather and add indoor options."
        }
      ],
      "temperature": 0.7
    }'
  ```

  ```python Python (OpenAI SDK) theme={null} theme={null}
  from openai import OpenAI

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

  conversation_history = [
      {"role": "system", "content": "You are a concise travel assistant."},
      {"role": "user", "content": "I will spend 2 days in Tokyo. Build a simple itinerary."},
      {"role": "assistant", "content": "Day 1: Asakusa and Ueno. Day 2: Shibuya and Meiji Shrine."},
  ]

  conversation_history.append(
      {"role": "user", "content": "Update it for rainy weather and add indoor options."}
  )

  response = client.chat.completions.create(
      model="gpt-5.4",
      messages=conversation_history,
      temperature=0.7,
  )

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

  ```javascript JavaScript (OpenAI SDK) theme={null} theme={null}
  import OpenAI from "openai";

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

  const conversationHistory = [
    { role: "system", content: "You are a concise travel assistant." },
    { role: "user", content: "I will spend 2 days in Tokyo. Build a simple itinerary." },
    { role: "assistant", content: "Day 1: Asakusa and Ueno. Day 2: Shibuya and Meiji Shrine." },
    { role: "user", content: "Update it for rainy weather and add indoor options." }
  ];

  const response = await client.chat.completions.create({
    model: "gpt-5.4",
    messages: conversationHistory,
    temperature: 0.7
  });

  console.log(response.choices[0].message.content);
  ```
</CodeGroup>

## Streaming

Set `stream=true` to receive Server-Sent Events from `/chat/completions`.
If `stream_options.include_usage` is not provided, CRUN enables it automatically so the stream can include usage information near the end.

<CodeGroup>
  ```bash cURL theme={null} theme={null}
  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": "system", "content": "You are a concise assistant."},
          {"role": "user", "content": "Write a two-line product description for a wireless keyboard."}
      ]
    }'
  ```

  ```python Python (OpenAI SDK) theme={null} theme={null}
  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 concise assistant."},
          {"role": "user", "content": "Write a two-line product description for a wireless keyboard."}
      ],
      stream=True,
      temperature=0.7,
  )



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

  ```javascript JavaScript (OpenAI SDK) theme={null} theme={null}
  import OpenAI from "openai";

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

  async function main() {
    const stream = await client.chat.completions.create({
      model: "gpt-5.4",
      messages: [
        { role: "system", content: "You are a concise assistant." },
        { role: "user", content: "Write a two-line product description for a wireless keyboard." }
      ],
      temperature: 0.7,
      stream: true,
    });

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

  main().catch(console.error);
  ```
</CodeGroup>

### Example Response

```text stream response theme={null} theme={null}
data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"S"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"le"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"ek"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" responsive"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" wireless"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" keyboard"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" designed"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" for"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" comfortable"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" typing"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" clutter"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"-free"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" productivity"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"  \n"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"Enjoy"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" reliable"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" connectivity"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" long"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" battery"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" life"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" a"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" compact"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" design"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" perfect"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" for"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" home"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" or"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" office"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":" use"}}]}

data: {"id":"","object":"chat.completion.chunk","created":0,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

data: {"id":"resp_0c628e55cfc393b50069cddfec989c81939cd408ac45285daa","object":"chat.completion.chunk","created":1775099884,"model":"gpt-5.4","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":17,"completion_tokens":40,"total_tokens":57,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0,"text_tokens":0,"image_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0,"text_tokens":0,"cached_tokens":0}}}

data: [DONE]
```

## Notes

* `max_tokens` and `max_completion_tokens` are both supported. The actual value is capped by the selected model's output limit.
* `max_output_tokens` is supported on `/responses` and is capped by the selected model's output limit.
* Additional OpenAI-compatible fields are accepted and passed through when supported by the upstream model.
* Billing is based on input and output token usage, with a model-specific minimum charge. The minimum value is usually 0.01.
* For new agentic or stateful work, prefer `/responses`. For existing chat clients, `/chat/completions` remains supported. The legacy `/completions` endpoint is only provided for compatibility and does not support `stream=true`.

## Related Resources

<CardGroup cols={3}>
  <Card title="Responses API" icon="sparkles" href="/models/llm/responses">
    Build with flexible input, stateful follow-ups, structured outputs, and tool-ready response items.
  </Card>

  <Card title="Messages API" icon="message-circle" href="/models/llm/messages">
    Use Anthropic-compatible messages, system prompts, tools, thinking, and streaming events.
  </Card>

  <Card title="Chat Completions API" icon="message" href="/models/llm/chat-completions">
    Full API reference for request parameters, streaming, and OpenAI-style error responses.
  </Card>

  <Card title="Account Credits" icon="wallet" href="/common-api/get-account-credits">
    Check your remaining credits before running large-volume language model workloads.
  </Card>

  <Card title="Pricing" icon="coins" href="https://crun.ai/pricing">
    Jump to the pricing page to compare billing across different models.
  </Card>
</CardGroup>