Choosing an AI API for summarization

What summarization needs

• Low input price
• Enough context for the document
• Faithful summaries without invented detail

Models that fit

Somnus column uses the minimum 2× credit; larger top-ups go further.

Cost example

1,000 requests of about 1,500 input and 400 output tokens on DeepSeek V4 Flash cost about $0.59 at list price — roughly $0.30 with Somnus credit.

Tips

• Split very long documents and summarise the summaries.
• Tell the model the target length and audience.
• Use cached input when you summarise the same source repeatedly.

Common mistakes

• Choosing a model on output price when your cost is almost all input.
• Not asking the model to quote or cite, which hides errors.

Example

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["SOMNUS_API_KEY"],
    base_url="https://gateway-production-c837.up.railway.app/v1",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[
      {"role": "user", "content": "Summarise this meeting transcript in five bullet points."}
    ],
)
print(resp.choices[0].message.content)

Questions

Related