fix: add Google models gemini-2.5-computer-use-preview-10-2025

[github-actions]

fix: add Google models gemini-2.5-computer-use-preview-10-2025

Closes #536

Source issue: #536

Summary

Field	Value
Provider	google
Primary model	gemini-2.5-computer-use-preview-10-2025
Changed models	gemini-2.5-computer-use-preview-10-2025
Added models	gemini-2.5-computer-use-preview-10-2025
Updated models	None
Verification sources	1 2 3 4 5 6 7 8

Verified metadata

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
gemini-2.5-computer-use-preview-10-2025	Gemini 2.5 Computer Use Preview (10-2025)		google	google	chat	input=128000, output=64000	in/out=1.25/10 per 1M	multimodal=true

Verification notes

Verification

Official sources consulted

1. https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025 — Verified model ID, input token limit (128,000), output token limit (64,000), multimodal input (image + text), text output, and preview status.
2. https://ai.google.dev/gemini-api/docs/pricing — Verified input pricing ($1.25/M tokens for prompts <= 200k), output pricing ($10.00/M tokens for prompts <= 200k). Confirmed no cache pricing is listed for this model. Notes that "Computer Use billing uses the Gemini 2.5 Pro SKU."
3. https://cloud.google.com/vertex-ai/generative-ai/pricing — Corroborated pricing: $1.25/M input, $10.00/M output for the standard tier.
4. https://ai.google.dev/gemini-api/docs/models — Confirmed model listed under "Tool and agent models" section.

Fields verified

Field	Value	Source
format	google	Matches Google AI provider convention
flavor	chat	Model accepts text+image input, produces text output
multimodal	true	Official model page: input types are image and text
max_input_tokens	128000	Official model page
max_output_tokens	64000	Official model page
input_cost_per_mil_tokens	1.25	Google AI pricing page
output_cost_per_mil_tokens	10	Google AI pricing page
available_providers	["google"]	Confirmed on Google AI (Gemini API). Vertex variant not verified.
displayName	Gemini 2.5 Computer Use Preview (10-2025)	Derived from official name "Gemini 2.5 Computer Use" + date suffix

Fields omitted (not published or not applicable)

• parent: No stable alias gemini-2.5-computer-use exists in model_list.json, so no parent relationship can be established.
• input_cache_read_cost_per_mil_tokens: Google pricing page does not list cache pricing for this model (only for Gemini 2.5 Pro base).
• input_cache_write_cost_per_mil_tokens: Not listed.
• reasoning / reasoning_budget: The official model page does not document thinking/reasoning token support for this model. It is described as an agentic computer-use model, not a thinking model.
• deprecation_date: Not published; model is in preview status.
• locations / supported_regions: Not required for google provider models.

sync_models (LiteLLM) cross-check

The model gemini-2.5-computer-use-preview-10-2025 has no entry in the LiteLLM model_prices_and_context_window_backup.json catalog (checked 2026-05-19). Therefore, no field-by-field comparison is possible. All proposed values are sourced directly from official Google documentation.

sync_models vs proposed update

sync_models cross-check found no pricing/token discrepancies for the changed models.

No sync_models discrepancies were noted.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview, Comment	May 19, 2026 8:43pm

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 34d3e6ac29

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".

[chatgpt-codex-connector]

Add Vertex provider for this Gemini computer-use model

This mapping hard-codes the new model as Google-only, but Google’s launch/docs for gemini-2.5-computer-use-preview-10-2025 state it is available on both Google AI Studio and Vertex AI; keeping it "google"-only causes provider selection helpers (for example getModelEndpointTypes, verification flows, and provider metadata consumers) to treat Vertex as unsupported for this model. Please include Vertex support here (and corresponding catalog/provider entries) so Vertex credentials can be selected for this model.

Useful? React with 👍 / 👎.

[Caitlin Pinn (cpinn)]

This does not work. Do not merge