anomalyco / anomalyco/models.dev

Differentiating token cost for TEXT and IMAGE

Open
#66 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
6.9k
Forks
1.7k
Avg merge
3h 21m
Merged PRs (30d)
873

Description

Currently we can not differentiate the cost between input modalities...

It would be great to create subsections for the cost section, for example for the gpt-image-1 it would look like:

[cost.image]

input = 10.00
output = 40.00
cache_read = 2.50

# I am not sure about the granularity of the decomposition of the following subsection (by quality or width/heigth first)[cost.image_generation]

low = {
  '1024_1024' : 0.011,
  '1024_1536' : 0.016,
  '1536_1024' : 0.016,
}

medium = #...

high = #....

[cost.text]

# ...

May be this would be adding too much complexity to the schema ?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the current cost schema and model data, then compare it with the proposed gpt-image-1 example in the issue. Determine how modality, quality, and dimensions should be represented without making the schema unnecessarily complex. Done means the schema can express distinct text and image costs and the affected model data uses the agreed structure.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, data
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.