Summary
Three Databricks Foundation Model API pay-per-token GPT models are missing from packages/proxy/schema/model_list.json. This is a follow-up to #559 , #585 , #591 , and #592 , continuing to address the Databricks catalog gap.
Missing Model IDs
Model ID
Context Window
Max Output
Supported Inputs
Underlying Model
databricks-gpt-5-4400,000
128,000
text, image
GPT-5.4
databricks-gpt-5-4-nano400,000
128,000
text, image
GPT-5.4 nano
databricks-gpt-5-2400,000
128,000
text, image
GPT-5.2
Details
All three models appear on both the Foundation model overview regional availability table and the Supported models page with documented context windows and max output tokens. They are available as pay-per-token serverless endpoints.
Suggested entries
"databricks-gpt-5-4" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.4" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"available_providers" : [" databricks" "databricks-gpt-5-4-nano" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.4 nano" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"available_providers" : [" databricks" "databricks-gpt-5-2" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.2" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"available_providers" : [" databricks" Pricing omitted per Databricks provider constraints (no stable public per-model pricing source).
Verification checklist
Cross-source : Model IDs confirmed on Foundation model overview and Supported models page Recent commits : Not covered by any recent commit to model_list.jsonID format : Follows existing databricks-<model> naming convention (e.g., databricks-meta-llama-3-3-70b-instruct)Existing issues : Not covered by [BOT ISSUE] Databricks: add missing databricks-claude-opus-4-7, databricks-claude-sonnet-4-6, databricks-gpt-5-5 #559 [BOT ISSUE] Databricks: add missing databricks-gpt-5-5-pro, databricks-gemini-3-5-flash, databricks-gpt-5-4-mini #585 [BOT ISSUE] Databricks: add missing databricks-llama-4-maverick, databricks-gpt-oss-120b, databricks-gemma-3-12b #591 [BOT ISSUE] Databricks: add missing databricks-claude-sonnet-4-5, databricks-claude-opus-4-6, databricks-claude-sonnet-4 #592
Verification notes
Field
Source
Notes
Model IDs
Foundation model overview + Supported models page
Listed in both pay-per-token model tables
Context windows (400K)
Supported models page
"400K total token context window with 128K maximum output tokens"
Max output (128K)
Supported models page
Same source as context window
format: "openai", flavor: "chat"Catalog convention
All Databricks models use openai format
multimodal: trueSupported models page
Inputs: text, image
input_cost_per_mil_tokens / output_cost_per_mil_tokensNOT PUBLISHED
Databricks does not publish stable per-model pricing
reasoningNOT VERIFIED
Not confirmed for Databricks-hosted versions
Local files inspected
packages/proxy/schema/model_list.json — grep for databricks-gpt-5-4" and databricks-gpt-5-2 returns no matches
Source URLs
{
"kind" : " missing_model" "provider" : " databricks" "models" : [" databricks-gpt-5-4" " databricks-gpt-5-4-nano" " databricks-gpt-5-2" "status" : " active" "model_specs" : {
"databricks-gpt-5-4" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.4" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"available_providers" : [" databricks" "databricks-gpt-5-4-nano" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.4 nano" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"available_providers" : [" databricks" "databricks-gpt-5-2" : {
"format" : " openai" "flavor" : " chat" "multimodal" : true ,
"displayName" : " GPT-5.2" "max_input_tokens" : 400000 ,
"max_output_tokens" : 128000 ,
"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" 
Summary
Three Databricks Foundation Model API pay-per-token GPT models are missing from
packages/proxy/schema/model_list.json. This is a follow-up to #559, #585, #591, and #592, continuing to address the Databricks catalog gap.Missing Model IDs
databricks-gpt-5-4databricks-gpt-5-4-nanodatabricks-gpt-5-2Details
All three models appear on both the Foundation model overview regional availability table and the Supported models page with documented context windows and max output tokens. They are available as pay-per-token serverless endpoints.
Suggested entries
Pricing omitted per Databricks provider constraints (no stable public per-model pricing source).
Verification checklist
model_list.jsondatabricks-<model>naming convention (e.g.,databricks-meta-llama-3-3-70b-instruct)databricks-llama-4-maverick,databricks-gpt-oss-120b,databricks-gemma-3-12b#591, or [BOT ISSUE] Databricks: add missingdatabricks-claude-sonnet-4-5,databricks-claude-opus-4-6,databricks-claude-sonnet-4#592Verification notes
format: "openai",flavor: "chat"multimodal: trueinput_cost_per_mil_tokens/output_cost_per_mil_tokensreasoningLocal files inspected
packages/proxy/schema/model_list.json— grep fordatabricks-gpt-5-4"anddatabricks-gpt-5-2returns no matchesSource URLs
{ "kind": "missing_model", "provider": "databricks", "models": ["databricks-gpt-5-4", "databricks-gpt-5-4-nano", "databricks-gpt-5-2"], "status": "active", "model_specs": { "databricks-gpt-5-4": { "format": "openai", "flavor": "chat", "multimodal": true, "displayName": "GPT-5.4", "max_input_tokens": 400000, "max_output_tokens": 128000, "available_providers": ["databricks"] }, "databricks-gpt-5-4-nano": { "format": "openai", "flavor": "chat", "multimodal": true, "displayName": "GPT-5.4 nano", "max_input_tokens": 400000, "max_output_tokens": 128000, "available_providers": ["databricks"] }, "databricks-gpt-5-2": { "format": "openai", "flavor": "chat", "multimodal": true, "displayName": "GPT-5.2", "max_input_tokens": 400000, "max_output_tokens": 128000, "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" ] }