one chat reply3,000 tokens in, 500 outGemini 3.1 Pro costs 1.1× as much as Claude Sonnet 5
$0.01
$0.01
summarise a 100-page report50,000 tokens in, 1,500 out, one requestwithin 5%
$0.12
$0.12
1,000 classification calls500 tokens in, 20 out, per call
$1.24
$1.20
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache
$4.72
$4.60
same session, cached85% of input read from the prompt cache, the rest written to it
$1.66
$1.69
at listed rates. token counts are typical sizes, not measurements.
Gemini 3.1 Pro pricing notes
once a request passes 200K input tokens, the whole request bills at $4 input, $18 output and $0.40 cache read per 1M; the listed price is the sub-200K rate.
output price includes thinking tokens.
Claude Sonnet 5 pricing notes
Anthropic made the $2 / $10 introductory rate permanent on 2026-08-10; the planned $3 / $15 rise was cancelled.
its updated tokenizer can turn the same text into roughly 1.0-1.35x as many tokens, by content type.
cache writes bill at the 5-minute rate ($2.50 per 1M); Anthropic's 1-hour tier ($4) is not modelled.
Google's Pro-tier Gemini model, released in preview as the reasoning-focused successor to Gemini 3 Pro at the same $2 / $12 rate. it takes text, images, video, audio and PDFs into a 1M-token window and returns text.
pick it if
you need audio, video or PDF input alongside text and images
you resend long prompts; cache hits bill at 10% of input
you want Google's Pro tier rather than a Flash model
skip it if
your prompts often exceed 200K tokens, where input doubles and output rises 1.5x
Claude Sonnet 5 was Anthropic's mid-tier Sonnet model, released June 2026 with adaptive thinking and text plus image input. it was retired in favour of Claude Sonnet 5.5, which kept the same $2 / $10 price.
pick it if
you wanted agentic work Anthropic placed close to Opus 4.8, at lower prices
you reused long prompts: cache reads billed at a tenth of input
you needed image input alongside adaptive thinking
skip it if
you are choosing today; Sonnet 5.5 replaced it at the same $2 / $10
faq
which is cheaper, Gemini 3.1 Pro or Claude Sonnet 5?
Claude Sonnet 5 lists the lower output price; input prices match. on a coding-agent session (2M tokens in, 60,000 out) Gemini 3.1 Pro costs $4.72 and Claude Sonnet 5 $4.60.
which has the larger context window?
Gemini 3.1 Pro offers the larger context window. Gemini 3.1 Pro: 1M tokens; Claude Sonnet 5: 200k tokens.
try either model
switch between models inside the same octomind session.