Skip to main content
POST
https://api.tracelm.ai
/
v1
/
chat
/
completions
Chat Completions
curl --request POST \
  --url https://api.tracelm.ai/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "temperature": 123,
  "max_tokens": 123,
  "stream": true,
  "tools": [
    {}
  ]
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {}
  ],
  "usage": {}
}
Creates a chat completion. This endpoint is fully compatible with the OpenAI Chat Completions API, with automatic tracing added.

​
Request

​
model
string
required
The model to use for the completion (e.g., gpt-4o-mini, gpt-4o, gpt-4-turbo)
​
messages
array
required
An array of messages in the conversation. Each message has:
  • role: system, user, assistant, or tool
  • content: The message content
​
temperature
number
Sampling temperature (0-2). Higher values make output more random.
​
max_tokens
integer
Maximum number of tokens to generate.
​
stream
boolean
Whether to stream the response. Defaults to false.
​
tools
array
A list of tools the model may call. See Working with Tool Calls.

​
Agent Headers (Optional)

​
X-Task-ID
string
Unique identifier for the current agent task.
​
X-Conversation-ID
string
Unique identifier for the user conversation/session.
​
X-User-ID
string
Your application’s user identifier.

​
Response

​
id
string
Unique identifier for the completion.
​
object
string
Always chat.completion.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used for the completion.
​
choices
array
An array of completion choices. Each choice has:
  • index: The index of the choice
  • message: The generated message
  • finish_reason: Why the model stopped (stop, length, tool_calls)
​
usage
object
Token usage information:
  • prompt_tokens: Tokens in the prompt
  • completion_tokens: Tokens in the completion
  • total_tokens: Total tokens used

​
Examples

​
Basic Request

curl -X POST "https://api.tracelm.ai/v1/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-API-Key: $TRACELM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7
  }'

​
Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677858242,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

​
With Tool Calls

curl -X POST "https://api.tracelm.ai/v1/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-API-Key: $TRACELM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "What is the weather in NYC?"}],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {"type": "string"}
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

​
Streaming

curl -X POST "https://api.tracelm.ai/v1/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-API-Key: $TRACELM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Write a poem"}],
    "stream": true
  }'
Streaming responses are sent as Server-Sent Events (SSE): 
data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"delta":{"content":"The"},"index":0}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"delta":{"content":" capital"},"index":0}]}

data: [DONE]

​
With Agent Headers

curl -X POST "https://api.tracelm.ai/v1/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-API-Key: $TRACELM_API_KEY" \
  -H "X-Task-ID: task_abc123" \
  -H "X-Conversation-ID: conv_xyz789" \
  -H "X-User-ID: user_456" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
When using agent headers, all traces are automatically grouped and detection is enabled.