Skip to content

chore: update model catalog from bot issues #876

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
Erin McNulty (erin2722) merged 2 commits into from
Jun 26, 2026
Merged

chore: update model catalog from bot issues #876

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
55006dc
chore: respond to codex review
erin2722 Jun 26, 2026
83678c8
fix: keep claude-sonnet-4-6 (vertex) max_output at 64000
erin2722 Jun 26, 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
7 changes: 7 additions & 0 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -583,6 +583,13 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"grok-2-1212": ["xAI"],
"grok-vision-beta": ["xAI"],
"grok-beta": ["xAI"],
"claude-sonnet-4-6": ["anthropic"],
"gemini-3.1-flash-image": ["google", "vertex"],
"publishers/google/models/gemini-3.1-flash-image": ["vertex"],
"grok-4.20-multi-agent-0309": ["xAI"],
"gpt-5-pro": ["openai", "azure"],
"gpt-5-pro-2025-10-06": ["openai", "azure"],
"gpt-5": ["openai", "azure"],
"gpt-5-2025-08-07": ["openai", "azure"],
"o3-2025-04-16": ["openai", "azure"],
"gpt-5-mini-2025-08-07": ["openai", "azure"],
Expand Down
38 changes: 37 additions & 1 deletion packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9324,7 +9324,7 @@
"displayName": "Claude Sonnet 4.6",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"available_providers": [
"vertex"
Expand Down Expand Up @@ -12931,6 +12931,26 @@
"vertex"
]
},
"gemini-3.1-flash-image": {
"format": "google",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.5,
"output_cost_per_mil_tokens": 3,
"displayName": "Gemini 3.1 Flash Image",
"fallback_models": [
"publishers/google/models/gemini-3.1-flash-image"
],
"supported_regions": [
"global"
],
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"available_providers": [
"google",
"vertex"
]
Comment on lines +12949 to +12952

@chatgpt-codex-connector chatgpt-codex-connector Bot Jun 26, 2026

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 Expose Gemini 3.1 Flash Image on Vertex

For Vertex-only installations, this new model will not be selectable because it advertises only the google provider and has no publisher fallback, while Google Cloud lists gemini-3.1-flash-image as available on the global endpoint (https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-1-flash-image#supported-regions). The adjacent stable image model (gemini-3-pro-image) includes both google and vertex plus a publishers/google/models/... fallback, so this omission prevents routing through supported Vertex credentials.

Useful? React with 👍 / 👎.

},
"publishers/google/models/gemini-2.5-computer-use-preview-10-2025": {
"format": "google",
"flavor": "chat",
Expand Down Expand Up @@ -12960,6 +12980,22 @@
"vertex"
]
},
"publishers/google/models/gemini-3.1-flash-image": {
"format": "google",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.5,
"output_cost_per_mil_tokens": 3,
"displayName": "Gemini 3.1 Flash Image",
"locations": [
"global"
],
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"available_providers": [
"vertex"
]
},
"databricks-qwen35-122b-a10b": {
"format": "openai",
"flavor": "chat",
Expand Down
Loading