feat(pricing): add Veo 3.1 Lite generate model

[Adityai1411]

Relevant issues

Closes #33199

Linear ticket

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have added meaningful tests
• My PR passes the relevant local checks for this isolated pricing-map change
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

Screenshots / Proof of Fix

Validated locally with:

• python -m pytest tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py -q
• python -m black --check tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py
• python -m json.tool model_prices_and_context_window.json
• python -m json.tool litellm/model_prices_and_context_window_backup.json
• git diff --check

Official sources:

• Model details: https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate
• Pricing: https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing

Type

? Test

Changes

• Added gemini/veo-3.1-lite-generate-001 to model_prices_and_context_window.json and the shipped backup map.
• Added vertex_ai/veo-3.1-lite-generate-001 alongside the existing Vertex AI Veo 3.1 GA entries.
• Added a regression test to keep the root and backup cost maps in sync for both provider entries.

[CLAassistant]

All committers have signed the CLA.

[greptile-apps]

Greptile Summary

This PR adds gemini/veo-3.1-lite-generate-001 and vertex_ai/veo-3.1-lite-generate-001 to both the root and backup cost maps, along with a regression test that verifies both provider entries exist and carry the expected fields in both files.

• Both JSON entries are well-formed, consistent with each other, and the output_cost_per_second: 0.05 (720p) value matches the official Gemini API pricing page. The 1080p pricing (0.08) mirrors the existing lite-generate-preview entry.
• The vertex_ai/veo-3.1-lite-generate-001 entry uses a source URL pointing to the Gemini Enterprise Agent Platform docs, while every other vertex_ai/veo-3.1-* entry in both files uses the Vertex AI generative-ai model-reference URL — a minor but visible inconsistency.
• The new test reads only local files, makes no network calls, and correctly covers both providers against both maps.

Confidence Score: 4/5

Safe to merge; the change is purely additive to two JSON cost maps with a matching test, and all pricing values align with the official Gemini API pricing page.

The new entries are well-formed and consistent with each other, and the test correctly validates both provider keys in both maps. The only notable issue is the source URL in the two vertex_ai entries, which points to the Gemini Enterprise Agent Platform docs instead of the Vertex AI model-reference URL used by every other vertex_ai/veo-3.1 entry — a cosmetic inconsistency that does not affect runtime behavior.

The source field in both model_prices_and_context_window.json and litellm/model_prices_and_context_window_backup.json for the vertex_ai/veo-3.1-lite-generate-001 entry.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds gemini/veo-3.1-lite-generate-001 and vertex_ai/veo-3.1-lite-generate-001 entries; pricing values match the Gemini API pricing page but the vertex_ai entry's source URL is inconsistent with all other vertex_ai/veo-3.1 entries
litellm/model_prices_and_context_window_backup.json	Backup map kept in sync with the root map; same source URL inconsistency for the vertex_ai entry is present here as well
tests/test_litellm/litellm_core_utils/test_get_model_cost_map.py	Adds test_veo_31_lite_generate_001_model_cost_map_entries; reads only local files (no network calls), checks both root and backup maps for all expected fields and both providers

_{Reviews (1): Last reviewed commit: "feat(pricing): add Veo 3.1 Lite generate..." | Re-trigger Greptile}

[greptile-apps]

The source for this vertex_ai entry points to the Gemini Enterprise Agent Platform docs, while every other vertex_ai/veo-3.1-* entry in this file (generate-preview, fast-generate-preview, generate-001, fast-generate-001) uses the Vertex AI generative-ai model-reference URL. This inconsistency could mislead developers looking up this model's authoritative documentation.

Suggested change

	"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
	"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

[greptile-apps]

Same inconsistency as in the root map: the source URL for this entry uses the Gemini Enterprise Agent Platform docs path rather than the Vertex AI generative-ai model-reference URL that all other vertex_ai/veo-3.1-* entries in the backup map use.

Suggested change

	"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
	"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo",

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[mateo-berri]

Superseded by #30782, which landed the same cost map entries plus resolution inference and tests. Thanks for the contribution!