[BOT ISSUE] Add databricks-gpt-5-4-mini and databricks-gemini-3-6-flash (Databricks)

Open Beginner friendly
#1,092 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
85/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Quiet
Tech stack
json
Domain
ai, backend

Research direction

Start by opening model_list.json and comparing nearby Databricks entries with the existing gpt-5.4-mini and gemini-3.6-flash records. Add the two missing catalog entries using the verified metadata in the issue, then confirm both model IDs appear in model_list.json with the expected provider and token limits.

Written by the indexing model from the issue text.

Description

autofix-blocked

Summary

Two models listed on the Databricks Foundation Model APIs docs for pay-per-token serverless inference are missing from the model catalog: databricks-gpt-5-4-mini and databricks-gemini-3-6-flash.

Gap

Both base models exist in the catalog (gpt-5.4-mini and gemini-3.6-flash), but the Databricks-specific endpoint names do not. Other models in the same series already have Databricks variants (e.g., databricks-gpt-5-4, databricks-gpt-5-4-nano, databricks-gemini-3-5-flash).

Source verification

databricks-gpt-5-4-mini
Field Value Source
Model ID databricks-gpt-5-4-mini Databricks Foundation Model docs
Base model gpt-5.4-mini Already in model_list.json (line 172)
Context window 272,000 input / 128,000 output Consistent with databricks-gpt-5-4-nano and Azure docs
Pricing Not published per-model by Databricks Skipped per provider constraint
databricks-gemini-3-6-flash
Field Value Source
Model ID databricks-gemini-3-6-flash Databricks Foundation Model docs
Base model gemini-3.6-flash Already in model_list.json (line 11122)
Context window 1,048,576 input / 65,536 output Consistent with databricks-gemini-3-5-flash
Pricing Not published per-model by Databricks Skipped per provider constraint

Cross-source verification

  • Both models confirmed on Databricks official documentation as available for pay-per-token serverless inference
  • Base model gpt-5.4-mini confirmed on OpenAI docs and OpenAI pricing
  • Base model gemini-3.6-flash confirmed on Google AI docs and Google pricing
  • Not present in model_list.json (grep confirmed zero matches for both IDs)
  • No existing GitHub issue covers these Databricks endpoints
  • Specs derived from existing Databricks entries in the same model families (databricks-gpt-5-4-nano, databricks-gemini-3-5-flash)

Notes

  • Databricks does not publish stable per-model pricing — pricing fields are omitted per provider constraint
  • Databricks entries use format: "openai" (not the base model's native format) since Databricks exposes an OpenAI-compatible API
  • reasoning is included for databricks-gemini-3-6-flash for consistency with the existing databricks-gemini-3-5-flash entry
Dominant language
TypeScript
Stars
410
Forks
65
Avg merge
18h 29m
Merged PRs (30d)
51

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.

More from braintrustdata/braintrust-proxy

All issues in braintrustdata/braintrust-proxy

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.