anomalyco / anomalyco/models.dev
Feature: add a separate OpenAI Codex provider for OAuth-specific model limits
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 6.9k
- Forks
- 1.7k
- Avg merge
- 3h 21m
- Merged PRs (30d)
- 873
Description
Proposal
Add a separate OpenAI Codex provider for models served through ChatGPT/Codex OAuth.
The main openai provider should continue describing direct API access. The Codex provider can inherit shared model metadata with base_model and override the limits that differ on the Codex backend. Harnesses such as OpenCode can then select the correct provider when Codex OAuth is active.
This has moved beyond a one-time client workaround: four current Codex models now have different limits from their direct API definitions.
Evidence
| Models | Direct OpenAI API | Codex OAuth |
|---|---|---|
gpt-5.5 |
1,050K context / 922K input / 128K output | 400K context / 272K input / 128K output |
gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna |
1,050K context / 922K input / 128K output | 500K context / 372K input / 128K output |
The Codex values can be independently checked with codex debug models. GPT-5.5 reports 272000; all three GPT-5.6 models report 372000.
Related
- GPT-5.5 mismatch: https://github.com/anomalyco/opencode/issues/24171
- GPT-5.5 client override: https://github.com/anomalyco/opencode/pull/24212
- Four-model issue: https://github.com/anomalyco/opencode/issues/36247
- GPT-5.6 client override: https://github.com/anomalyco/opencode/pull/36248
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Locate the existing OpenAI provider definitions and shared model metadata, then compare their structure with the proposal. Use codex debug models to verify the OAuth limits, and consider the work complete when a separate Codex provider can inherit the shared metadata while exposing the four listed models' distinct limits.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100