Cost Metadata

While most standard LLM APIs return usage metrics (like input and output token counts), they typically don't provide the actual monetary cost of the request. Developers are often left to calculate this themselves, requiring them to maintain and apply up-to-date pricing information for each model.

AnotherAI simplifies cost tracking by automatically calculating the estimated cost for each LLM request based on the specific model used and AnotherAI's current pricing data.

Programmatically

The cost and latency information are added to each choice in the response:

import openai

client = openai.OpenAI(
    api_key="YOUR_ANOTHERAI_API_KEY",
    base_url="https://api.anotherai.dev/v1"
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
    metadata={"agent_id": "my-agent"}
)

# Access cost and latency from the first choice
cost = getattr(completion.choices[0], 'cost_usd', None)
latency = getattr(completion.choices[0], 'duration_seconds', None)

print(f"Cost: ${cost:.6f}")
print(f"Latency: {latency:.2f}s")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_ANOTHERAI_API_KEY',
  baseURL: 'https://api.anotherai.dev/v1',
});

const completion = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{ role: 'user', content: 'Hello!' }],
  metadata: { agent_id: 'my-agent' }
});

// Access cost and latency from the first choice
const cost = completion.choices[0].cost_usd;
const latency = completion.choices[0].duration_seconds;

console.log(`Cost: $${cost.toFixed(6)}`);
console.log(`Latency: ${latency.toFixed(2)}s`);

curl https://api.anotherai.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_ANOTHERAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}],
    "metadata": {"agent_id": "my-agent"}
  }'

# Response includes cost_usd and duration_seconds in each choice:
# {
#   "choices": [{
#     "message": {...},
#     "cost_usd": 0.000015,
#     "duration_seconds": 1.23
#   }],
#   ...
# }

from pydantic import BaseModel
import instructor

client = instructor.from_openai(
    openai.OpenAI(
        api_key="YOUR_ANOTHERAI_API_KEY",
        base_url="https://api.anotherai.dev/v1"
    )
)

class Answer(BaseModel):
    sentiment: str
    score: float

answer, completion = client.chat.completions.create_with_completion(
    model="gpt-4o-mini",
    response_model=Answer,
    messages=[{"role": "user", "content": "I love AnotherAI!"}],
    metadata={"agent_id": "sentiment-analysis-agent"}
)

# Access cost and latency from the completion
cost = getattr(completion.choices[0], 'cost_usd', None)
latency = getattr(completion.choices[0], 'duration_seconds', None)

print(f"Sentiment: {answer.sentiment}, Score: {answer.score}")
print(f"Cost: ${cost:.6f}, Latency: {latency:.2f}s")

Tracking Costs

Via MCP

Ask questions about costs in natural language using Claude Code:

What's the total cost for my-agent since January 1st, 2024?

Show me the sum of all costs for my-agent completions created after 2024-01-01

Creating Cost Views in AnotherAI

Track spending across agents with custom views:

Create a view in AnotherAI that shows daily costs for calendar_event_extractor.py

Create a view showing total monthly spend across all agents, by agent_id, with a line chart

Create a cost breakdown view showing spend by model across all agents

Cost Metadata

Programmatically

Tracking Costs

Via MCP

Creating Cost Views in AnotherAI

On this page