Generate a response using the OpenAI Chat Completions format. This endpoint is compatible with the OpenAI SDK and Codex CLI.

Endpoint

POST https://api.runars.ca/v1/chat/completions

Authentication

Include your API key as a Bearer token:

-H "Authorization: Bearer sk-runars-..."

Request body

For a comparison of common parameters across all endpoints, see Parameters Reference.

Field	Type	Required	Description
`model`	string	Yes	Model identifier, must be `"glm-5.2"`
`messages`	array	Yes	Array of message objects with `role` and `content`
`max_tokens`	integer	No	Maximum tokens in the response (default: unlimited)
`temperature`	number	No	Sampling temperature (0–2, default: 1)
`top_p`	number	No	Nucleus sampling threshold (0–1)
`stream`	boolean	No	Enable streaming (default: false)
`tools`	array	No	Array of tool/function definitions (optional for tool calling)
`tool_choice`	string\|object	No	Which tool to use (`"auto"`, `"required"`, or specific tool)
`stream_options`	object	No	Streaming options, including `include_usage`

Message format

Each message in the messages array:

{
  "role": "user" or "assistant",
  "content": "text content"
}

Or with tool calls:

{
  "role": "assistant",
  "content": "Optional text",
  "tool_calls": [
    {
      "id": "call_...",
      "type": "function",
      "function": {
        "name": "tool_name",
        "arguments": "{...}"
      }
    }
  ]
}

Response (non-streaming)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "glm-5.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The response text here."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 15,
    "total_tokens": 57
  }
}

Response (streaming)

With stream: true, the endpoint returns server-sent events:

event: message_start
data: {"object":"chat.completion","model":"glm-5.2",...}

event: message_delta
data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":""}}]}

event: message_delta
data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"The "}}]}

event: message_delta
data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"response "}}]}

event: message_stop
data: {"object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

Examples

Simple text request

curl https://api.runars.ca/v1/chat/completions \
  -H "Authorization: Bearer sk-runars-..." \
  -H "content-type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [
      {
        "role": "user",
        "content": "What is the capital of France?"
      }
    ]
  }'

Using the OpenAI SDK with streaming

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://api.runars.ca/v1",
  apiKey: process.env.OPENAI_API_KEY,
})

const stream = await openai.chat.completions.create({
  model: "glm-5.2",
  messages: [
    {
      role: "user",
      content: "Tell me a short story about a robot.",
    },
  ],
  stream: true,
})

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

With tool calling

curl https://api.runars.ca/v1/chat/completions \
  -H "Authorization: Bearer sk-runars-..." \
  -H "content-type: application/json" \
  -d '{
    "model": "glm-5.2",
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the current weather",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "City name"
              }
            },
            "required": ["location"]
          }
        }
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in Toronto?"
      }
    ]
  }'

The response will include a tool_calls array with the tool name and arguments. You can then send the tool result back in a subsequent message.

Streaming with usage tracking

To get token usage in a streaming response, pass stream_options:

curl https://api.runars.ca/v1/chat/completions \
  -H "Authorization: Bearer sk-runars-..." \
  -H "content-type: application/json" \
  -d '{
    "model": "glm-5.2",
    "stream": true,
    "stream_options": {
      "include_usage": true
    },
    "messages": [
      {
        "role": "user",
        "content": "Say hello"
      }
    ]
  }'

The final message will include usage data.

Error responses

400 Bad Request

Invalid request:

{
  "error": {
    "message": "Invalid request: missing required field 'messages'",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

401 Unauthorized

Invalid or missing API key:

{
  "error": {
    "message": "Unauthorized",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

429 Too Many Requests

Rate limit exceeded:

{
  "error": {
    "message": "Rate limit exceeded",
    "type": "server_error",
    "param": null,
    "code": "insufficient_quota"
  }
}

The response includes a Retry-After header indicating how long to wait.

Token usage

Prompt tokens: Input tokens (messages + any system prompt).
Completion tokens: Output tokens.
Total tokens: Sum of prompt and completion tokens.

All count towards pricing and rate limits. See Pricing for rates.

POST /v1/chat/completions