[BOT ISSUE] Google: add missing gemini-3.1-flash-lite-image model

[github-actions]

Summary

Google's gemini-3.1-flash-lite-image is a GA (Stable) multimodal model for ultra-low latency image generation and editing, launched in June 2026. It is the budget-tier image variant that complements the already-cataloged gemini-3.1-flash-image (the faster/larger variant) and gemini-3.1-flash-lite (text-only variant).

The catalog includes every other Gemini image model (gemini-3.1-flash-image, gemini-3-pro-image, gemini-2.5-flash-image) but is missing this flash-lite image variant and its Vertex counterpart.

Missing Model IDs

Model ID	Provider	Status
gemini-3.1-flash-lite-image	google, vertex	GA (Stable)
publishers/google/models/gemini-3.1-flash-lite-image	vertex	GA (Stable)

Verified Specifications

Field	Value	Source
format	"google"	Pattern from gemini-3.1-flash-image
flavor	"chat"	Pattern from gemini-3.1-flash-image
multimodal	true	Google AI models page
input_cost_per_mil_tokens	0.25	Google AI pricing page — matches gemini-3.1-flash-lite text I/O pricing
output_cost_per_mil_tokens	1.5	Google AI pricing page
max_input_tokens	65536	Google AI models page
max_output_tokens	4096	Google AI models page
displayName	"Gemini 3.1 Flash-Lite Image"	Pattern from sibling entries
available_providers (Google AI entry)	["google", "vertex"]	Pattern from gemini-3.1-flash-image; Vertex availability confirmed on Vertex AI docs
supported_regions / locations	["global"]	Pattern from gemini-3.1-flash-image

Sibling comparison

Model	Input $/MTok	Output $/MTok	Max Input	Max Output
gemini-3.1-flash-lite (text)	$0.25	$1.50	1,048,576	65,536
gemini-3.1-flash-lite-image (missing)	$0.25	$1.50	65,536	4,096
gemini-3.1-flash-image	$0.50	$3.00	131,072	32,768

Verification Checklist

Check	Status	Detail
Cross-source	✅	Listed on both Google AI models page (model listing with specs) AND Google AI pricing page (pricing table)
Already fixed	✅	No flash-lite-image entries exist anywhere in packages/proxy/schema/
ID format	✅	Matches naming convention: gemini-3.1-flash-image, gemini-3.1-flash-lite, gemini-2.5-flash-image
Duplicate check	✅	No open issue covers this model ID

Verification Notes

• Input/output pricing ($0.25/$1.50) is verified from the Google AI pricing page for text I/O. Image output pricing is separate ($30/MTok for image output tokens) but the catalog tracks text I/O pricing only.
• Token limits (65K input / 4K output) are from the Google AI models page. These are significantly smaller than the text-only gemini-3.1-flash-lite (1M/65K), consistent with the image generation use case.
• reasoning field is intentionally omitted following the pattern of other catalog image models (gemini-3.1-flash-image, gemini-3-pro-image, gemini-2.5-flash-image), even though Google lists "Thinking" as a supported capability.
• Cache pricing is not included because the Google AI models page lists caching as "not supported" for this model.

Local Files Inspected

• packages/proxy/schema/model_list.json — confirmed no flash-lite-image entries exist
• packages/proxy/schema/index.ts — confirmed no flash-lite-image entries exist
• Sibling entries: gemini-3.1-flash-image (line ~11792), gemini-3.1-flash-lite (line ~6094), publishers/google/models/gemini-3.1-flash-image (line ~11841)

{
  "kind": "missing_model",
  "provider": "google",
  "models": ["gemini-3.1-flash-lite-image", "publishers/google/models/gemini-3.1-flash-lite-image"],
  "status": "active",
  "model_specs": {
    "gemini-3.1-flash-lite-image": {
      "format": "google",
      "flavor": "chat",
      "multimodal": true,
      "input_cost_per_mil_tokens": 0.25,
      "output_cost_per_mil_tokens": 1.5,
      "displayName": "Gemini 3.1 Flash-Lite Image",
      "fallback_models": ["publishers/google/models/gemini-3.1-flash-lite-image"],
      "supported_regions": ["global"],
      "max_input_tokens": 65536,
      "max_output_tokens": 4096,
      "available_providers": ["google", "vertex"]
    },
    "publishers/google/models/gemini-3.1-flash-lite-image": {
      "format": "google",
      "flavor": "chat",
      "multimodal": true,
      "input_cost_per_mil_tokens": 0.25,
      "output_cost_per_mil_tokens": 1.5,
      "displayName": "Gemini 3.1 Flash-Lite Image",
      "locations": ["global"],
      "max_input_tokens": 65536,
      "max_output_tokens": 4096,
      "available_providers": ["vertex"]
    }
  },
  "source_urls": [
    "https://ai.google.dev/gemini-api/docs/models/gemini",
    "https://ai.google.dev/pricing"
  ]
}

[github-actions]

Prepared catalog updates for gemini-3.1-flash-lite-image, publishers/google/models/gemini-3.1-flash-lite-image. Added models: gemini-3.1-flash-lite-image, publishers/google/models/gemini-3.1-flash-lite-image.

Verification sources: https://ai.google.dev/gemini-api/docs/models/gemini, https://ai.google.dev/pricing, https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini
Verified metadata applied:

• gemini-3.1-flash-lite-image: format=google, flavor=chat, displayName=Gemini 3.1 Flash-Lite Image, max_input_tokens=65536, max_output_tokens=4096, pricing(input/output per 1M)=0.25/1.5, providers=google|vertex, supported_regions=global, multimodal=true
• publishers/google/models/gemini-3.1-flash-lite-image: format=google, flavor=chat, displayName=Gemini 3.1 Flash-Lite Image, max_input_tokens=65536, max_output_tokens=4096, pricing(input/output per 1M)=0.25/1.5, providers=vertex, locations=global, multimodal=true

Included in the daily batch PR: #909