Usage

haimaker returns the OpenAI compatible usage object across all providers.

"usage": {
    "prompt_tokens": int,
    "completion_tokens": int,
    "total_tokens": int
}

Quick Start

from openai import OpenAI

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

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello, how are you?"}]
)

print(response.usage)
# Usage(prompt_tokens=12, completion_tokens=9, total_tokens=21)

print(f"Prompt tokens: {response.usage.prompt_tokens}")
print(f"Completion tokens: {response.usage.completion_tokens}")
print(f"Total tokens: {response.usage.total_tokens}")

Streaming Usage

When streaming, set stream_options={"include_usage": True} to receive usage statistics. An additional chunk will be streamed before the [DONE] message containing the token usage for the entire request.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    stream=True,
    stream_options={"include_usage": True}
)

for chunk in response:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")
    if chunk.usage:
        print(f"\n\nUsage: {chunk.usage}")

cURL

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Response includes usage:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1694268190,
  "model": "gpt-4o",
  "choices": [...],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 12,
    "total_tokens": 20
  }
}