[devin-ai-integration]

Summary

The Gemini API pricing page changed. Comparing it with the gemini/ rows turned up one price change and two deprecations, so this updates three gemini/ rows. Every value comes from the raw page fetched with a cache buster

Rows

gemini/gemini-3.5-flash-lite (kind page, source https://ai.google.dev/gemini-api/docs/pricing). cache_read_input_token_cost_batches goes from 2e-08 to 1.5e-08. The Batch tab "Context caching price" cell now reads "$0.015 / $1.00 / 1,000,000 tokens per hour (storage price)" where it used to read $0.02. The Flex tab still says $0.02, so cache_read_input_token_cost_flex stays 2e-08

gemini/gemini-2.5-pro (kind page, source https://ai.google.dev/gemini-api/docs/deprecations). Adds deprecation_date: 2026-12-01 from the deprecations table row "gemini-2.5-pro | June 17, 2025 | December 1, 2026 | gemini-3.8-flash". The pricing page callout says "Effective December 1, 2026, all API requests to gemini-2.5-pro will automatically route to Gemini 3.8 Flash (gemini-3.8-flash) and be billed at Gemini 3.8 Flash rates". Prices stay as they are until that day

gemini/gemini-2.5-flash (kind page, source https://ai.google.dev/gemini-api/docs/deprecations). Adds deprecation_date: 2026-12-01 from the row "gemini-2.5-flash | June 17, 2025 | December 1, 2026 | gemini-3.5-flash-lite". The page also says "gemini-2.5-flash-lite is not deprecated and remains available through the API until further notice", so that row is left alone

Left as is

The Batch, Flex and Priority tabs are gone from the Gemini 3 Pro Image section, and the Batch tab is gone from the Gemini 3.1 Flash Image section. Only Standard is listed now. The tier prices on gemini/gemini-3-pro-image, gemini/nano-banana-pro-preview, gemini/gemini-3-pro-image-preview and gemini/gemini-3.1-flash-image stay as they are until someone decides whether to drop them

The changelog dated November 2, 2026 only covers the 2.5 Pro and 2.5 Flash deprecations above

Delisted by the provider

gemini/veo-3.1-generate-preview, gemini/veo-3.1-fast-generate-preview and gemini/veo-3.1-lite-generate-preview already carry deprecation_date: 2026-10-22. The other 14 delisted ids are kept under ruling gemini-delisted-no-date-keep

Rulings followed

The new list ids stay out under the leave_out rulings antigravity-leave-out, gemini-aqa-leave-out, gemini-4-carbon-eap-leave-out-for-now, gemini-decision-eap-leave-out-until-priced and gemini-chatter-leave-out-until-priced. The Contributor tier prices stay out under gemini-contributor-tier-prices-leave-out. Gemini 4 Argon keeps its current prices under gemini-4-argon-dec-2026-price-change-keep-current

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[codspeed]

Merging this PR will not alter performance

1 warning

⚠️ 1 benchmark is dominated by system calls

System calls cannot be simulated consistently and are left out of the measure. The reported value understates the real cost. Switch to the Walltime instrument to measure them.

Learn more about system calls

See affected benchmarks

✅ 43 untouched benchmarks

---

_{Comparing litellm-providers/price-sync-gemini (cf41ebc) with main (baddc67)}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!