Skip to content

add gemini 3.1-flash-lite for vertex #600

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Ken Jiang (knjiang) merged 2 commits into from
May 20, 2026
Merged

add gemini 3.1-flash-lite for vertex #600

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f825d67
add gemini 3.1-flash-lite for vertex
knjiang May 20, 2026
e966ee8
fixxx
knjiang May 20, 2026
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
5 changes: 3 additions & 2 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -598,9 +598,8 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mistral-medium-3": ["mistral"],
"mistral-medium-3-5-26-04": ["mistral"],
"gemini-3.5-flash": ["google", "vertex"],
"publishers/google/models/gemini-3.5-flash": ["google"],
"deepseek.v3.2": ["bedrock"],
"gemini-3.1-flash-lite": ["google"],
"gemini-3.1-flash-lite": ["google", "vertex"],
"amazon.nova-premier-v1:0": ["bedrock"],
"amazon.nova-2-lite-v1:0": ["bedrock"],
"magistral-medium-2509": ["mistral"],
Expand Down Expand Up @@ -881,8 +880,10 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"gemini-3.1-flash-lite-preview": ["google"],
"gemini-3-pro-image-preview": ["google"],
"gemini-3-flash-preview": ["google"],
"publishers/google/models/gemini-3.5-flash": ["vertex"],
"publishers/google/models/gemini-3.1-pro-preview": ["vertex"],
"publishers/google/models/gemini-3.1-pro-preview-customtools": ["vertex"],
"publishers/google/models/gemini-3.1-flash-lite": ["vertex"],
"publishers/google/models/gemini-3.1-flash-lite-preview": ["vertex"],
"publishers/google/models/gemini-3-pro-preview": ["vertex"],
"publishers/google/models/gemini-3-flash-preview": ["vertex"],
Expand Down
32 changes: 32 additions & 0 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8543,6 +8543,22 @@
"max_input_tokens": 1048576,
"max_output_tokens": 65535
},
"publishers/google/models/gemini-3.1-flash-lite": {
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot May 20, 2026

Choose a reason for hiding this comment

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

P2 Badge Add endpoint type metadata for new Vertex model

This new publishers/google/models/... entry is added only in model_list.json, but getModelEndpointTypes() in packages/proxy/schema/index.ts first checks the hardcoded AvailableEndpointTypes map and otherwise falls back to the model format default (google). In the lookup-failed path (packages/proxy/edge/index.ts), that fallback is used to infer secret type, so this model will be treated as Google API instead of Vertex and requests can be routed to the wrong provider when users rely on direct-key fallback behavior.

Useful? React with 👍 / 👎.

"format": "google",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.25,
"output_cost_per_mil_tokens": 1.5,
"input_cache_read_cost_per_mil_tokens": 0.025,
"displayName": "Gemini 3.1 Flash-Lite",
"reasoning": true,
"reasoning_budget": true,
"locations": [
"global"
],
"max_input_tokens": 1048576,
"max_output_tokens": 65536
},
"publishers/google/models/gemini-3-pro-preview": {
"format": "google",
"flavor": "chat",
Expand All @@ -8559,6 +8575,22 @@
"max_input_tokens": 1048576,
"max_output_tokens": 65535
},
"publishers/google/models/gemini-3.5-flash": {
"format": "google",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 1.5,
"output_cost_per_mil_tokens": 9,
"input_cache_read_cost_per_mil_tokens": 0.15,
"displayName": "Gemini 3.5 Flash",
"reasoning": true,
"reasoning_budget": true,
"locations": [
"global"
],
"max_input_tokens": 1048576,
"max_output_tokens": 65535
},
"publishers/google/models/gemini-3-flash-preview": {
"format": "google",
"flavor": "chat",
Expand Down
Loading