Skip to content

Claude Sonnet 4.5 → Gemini 3.1 Pro: cost per request on six tasks

Gemini 3.1 Pro costs 22–33% less than Claude Sonnet 4.5 per request on six common tasks. It costs no more per result that works if its results work first time at least 68% as often as Claude Sonnet 4.5's on search re-ranking, and 78% as often on translation. Anthropic has announced Claude Sonnet 4.5's API shutdown for 2026-11-30.

List prices per million tokens

ModelInputCached inputOutput
Claude Sonnet 4.5$3.00$0.30$15.00
Gemini 3.1 Pro$2.00$0.20$12.00

Prices checked 2026-11-12.

Cost per 1,000 requests

TaskClaude Sonnet 4.5Gemini 3.1 ProChangeCheaper per result that works if it works first time at least
Support bot answerInstructions, three help-centre passages and the customer's question in; a short answer out.$13.50$9.6029% less72% as often as Claude Sonnet 4.5
Invoice field extractionInstructions and one invoice's text in; about 15 fields as JSON out.$11.25$8.0029% less72% as often as Claude Sonnet 4.5
Lead scoringScoring rules and one lead's form answers in; a score and a one-line reason out.$5.10$3.6029% less71% as often as Claude Sonnet 4.5
Email reply draftInstructions and the email thread so far in; a reply of about 300 words out.$10.50$7.8026% less75% as often as Claude Sonnet 4.5
TranslationInstructions and about 500 words of text in; the same text in another language out.$14.70$11.4022% less78% as often as Claude Sonnet 4.5
Search re-rankingA search query and 20 result snippets in; the ids of the best five, in order, out.$12.75$8.6033% less68% as often as Claude Sonnet 4.5

Token counts are typical sizes, not measurements.

Claude Sonnet 4.5 is being shut down

Anthropic has announced Claude Sonnet 4.5's API shutdown for 2026-11-30, with claude-sonnet-5-5 as the replacement (source).

Test it on your own prompt

The model switch test runs your prompt on both models side by side with your own API key, in your browser.

See every model's price