Skip to content

[BOT ISSUE] Google: add missing gemini-omni-1.1-flash model #1197

Description

@github-actions

Gap description

The Google Gemini model gemini-omni-1.1-flash is listed on both the Google AI models page and the Google AI pricing page, but is missing from the catalog. This is the stable/versioned variant of the Gemini Omni Flash model family — the preview variant (gemini-omni-flash-preview) is tracked separately in #1002.

Missing model ID

model ID displayName input $/1M output (text) $/1M output (video) $/1M
gemini-omni-1.1-flash Gemini Omni 1.1 Flash $1.50 $9.00 $17.50

Google describes this model as offering "Fast video generation, editing, keyframe interpolation, and extension with native audio." It appears under the Gemini 3 section on the models page and is listed as paid-tier only on the pricing page.

Suggested catalog entry

"gemini-omni-1.1-flash": {
  "format": "google",
  "flavor": "chat",
  "multimodal": true,
  "input_cost_per_mil_tokens": 1.5,
  "output_cost_per_mil_tokens": 9,
  "displayName": "Gemini Omni 1.1 Flash",
  "experimental": true,
  "available_providers": ["google"]
}

Notes on specific fields

  • output_cost_per_mil_tokens: Set to $9.00 (text output rate). Video output at $17.50/M tokens is a separate modality and may need a different field or documentation note.
  • experimental: Set to true because the Google AI models page lists this under the "Gemini 3 Preview" section, though the pricing page describes it as "generally available on the paid tier."
  • max_input_tokens / max_output_tokens: Not published on the pricing or models page. Should be verified from the API or model detail docs before adding.
  • Vertex AI: Not currently listed on the Vertex AI pricing page — only available via the direct Google AI API.

Sources

  • Google AI Developer Pricing — lists gemini-omni-1.1-flash with pricing: input $1.50, text output $9.00, video output $17.50 (paid tier only, no free tier)
  • Google AI Model Cards — lists gemini-omni-1.1-flash under Gemini 3 section as "Fast video generation, editing, keyframe interpolation, and extension with native audio"

Verification checklist

  • Cross-source: Model confirmed on (1) Google AI pricing page AND (2) Google AI models docs page
  • Already-fixed check: Grepped model_list.json for gemini-omni — no matches
  • ID format check: Follows standard Gemini naming convention (gemini-{family}-{version}-{variant})
  • Duplicate issue check: Searched open issues for gemini-omni-1.1 — no results. Separate from [BOT ISSUE] Google: add missing gemini-omni-flash-preview model #1002 which covers the preview variant only.
  • Not excluded: Not embedding, not vision-only (accepts text/image input, outputs text + video), not deprecated

Catalog precedent

The catalog includes similar Gemini multimodal generation models:

  • gemini-3.1-flash-image
  • gemini-3.1-flash-lite-image
  • gemini-3-pro-image
  • gemini-2.5-flash-image

Related issues

{
  "kind": "missing_model",
  "provider": "google",
  "models": ["gemini-omni-1.1-flash"],
  "model_specs": {
    "gemini-omni-1.1-flash": {
      "format": "google",
      "flavor": "chat",
      "multimodal": true,
      "input_cost_per_mil_tokens": 1.5,
      "output_cost_per_mil_tokens": 9,
      "displayName": "Gemini Omni 1.1 Flash",
      "experimental": true,
      "available_providers": ["google"]
    }
  },
  "source_urls": [
    "https://ai.google.dev/pricing",
    "https://ai.google.dev/gemini-api/docs/models"
  ]
}

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    autofix-blockedBot issue is blocked until metadata or source information is updated.bot-issue

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions