Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions packages/proxy/schema/index.ts
Original file line number Diff line number Diff line change
Expand Up @@ -590,6 +590,9 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"grok-2-1212": ["xAI"],
"grok-vision-beta": ["xAI"],
"grok-beta": ["xAI"],
"databricks-gpt-5": ["databricks"],
"databricks-gpt-5-1": ["databricks"],
"databricks-gpt-5-mini": ["databricks"],
"grok-4.20-0309-non-reasoning": ["xAI"],
"accounts/fireworks/models/deepseek-v4-flash": ["fireworks"],
"accounts/fireworks/models/glm-5": ["fireworks"],
Expand Down
33 changes: 33 additions & 0 deletions packages/proxy/schema/model_list.json
Original file line number Diff line number Diff line change
Expand Up @@ -9215,6 +9215,39 @@
"databricks"
]
},
"databricks-gpt-5": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5",
"max_input_tokens": 400000,
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Set GPT-5 Databricks input limit to the real prompt cap

max_input_tokens is documented in this repo as an input-only limit, but these new Databricks GPT-5 entries set it to 400000 (the total context window) instead of the effective prompt cap used elsewhere for GPT-5-family models (272000). This overstates capacity by 128k tokens, so any caller that trusts model metadata can send prompts that pass local checks but are rejected upstream for token-limit overflow.

Useful? React with 👍 / 👎.

"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gpt-5-1": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5.1",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gpt-5-mini": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5 mini",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"text-block": {
"format": "js",
"flavor": "completion",
Expand Down