[BOT ISSUE] Databricks: add missing databricks-gemini-3-6-flash

Open Beginner friendly
#1,053 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
1/5
Estimated time
Under an hour
Newbie friendliness
78/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Quiet
Tech stack
json
Domain
api, backend

Research direction

Open packages/proxy/schema/model_list.json and compare the existing databricks-gemini-3-5-flash entry near line 12811 with the base gemini-3.6-flash entry near line 11265. Add the missing catalog entry using the issue's specified fields, then validate that the JSON remains valid and the new model ID is present.

Written by the indexing model from the issue text.

Description

autofix-blocked

Gap description

The Databricks Foundation Model API pay-per-token endpoint databricks-gemini-3-6-flash is listed on official Databricks documentation but absent from packages/proxy/schema/model_list.json. The base model gemini-3.6-flash already exists in the catalog (line 11265) for google/vertex providers, and the sibling databricks-gemini-3-5-flash already exists (line 12811).

Missing Model

Model ID Display Name Base Model Context Window Max Output
databricks-gemini-3-6-flash Gemini 3.6 Flash gemini-3.6-flash (line 11265) 1,048,576 65,536

Context

  • The catalog already has 10+ databricks-gemini-* entries including databricks-gemini-3-5-flash, databricks-gemini-3-5-flash-lite, databricks-gemini-3-1-flash-lite, etc.
  • The base model gemini-3.6-flash exists at line 11265 with available_providers: ["google", "vertex", "openrouter"]
  • Databricks uses DBU-based pricing, so per-token dollar pricing is not available

Suggested Catalog Entry

"databricks-gemini-3-6-flash": {
  "format": "openai",
  "flavor": "chat",
  "multimodal": true,
  "displayName": "Gemini 3.6 Flash",
  "reasoning": true,
  "max_input_tokens": 1048576,
  "max_output_tokens": 65536,
  "available_providers": ["databricks"]
}

Verification Checklist

Check Status Detail
Cross-source ✅ Listed on Databricks Foundation Model Overview (pay-per-token table, multiple regions) AND Databricks Supported Models (endpoint name, input types, description)
Already in catalog ✅ databricks-gemini-3-6-flash does not exist in model_list.json
ID format ✅ Follows established databricks-gemini-* naming convention (e.g., databricks-gemini-3-5-flash, databricks-gemini-3-1-flash-lite)
Duplicate issue ✅ No open or closed issue covers databricks-gemini-3-6-flash
Not deprecated ✅ Actively listed across multiple regions on Databricks
Not embedding/vision-only ✅ Multimodal chat model (text, image, video, audio inputs)

Verification Notes

Field Source Notes
Model ID databricks-gemini-3-6-flash Databricks Foundation Model Overview + Supported Models pages Listed in pay-per-token endpoint tables across multiple regions
format: "openai" Catalog convention All Databricks models use openai format
reasoning: true Base model entry (gemini-3.6-flash at line 11265) Base model has reasoning: true
multimodal: true Databricks Supported Models page Supports text, image, video, audio inputs
Token limits Base model entry Matched to gemini-3.6-flash: 1,048,576 input / 65,536 output
Pricing Not published Databricks uses DBU-based pricing, not per-token dollar pricing

Local Files Inspected

  • packages/proxy/schema/model_list.json — confirmed databricks-gemini-3-6-flash absent; base model gemini-3.6-flash at line 11265; sibling databricks-gemini-3-5-flash at line 12811 used as template
{
  "kind": "missing_model",
  "provider": "databricks",
  "models": ["databricks-gemini-3-6-flash"],
  "status": "active",
  "model_specs": {
    "databricks-gemini-3-6-flash": {
      "format": "openai",
      "flavor": "chat",
      "multimodal": true,
      "displayName": "Gemini 3.6 Flash",
      "reasoning": true,
      "max_input_tokens": 1048576,
      "max_output_tokens": 65536,
      "available_providers": ["databricks"]
    }
  },
  "source_urls": [
    "https://docs.databricks.com/aws/en/machine-learning/model-serving/foundation-model-overview",
    "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
  ]
}
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.