Is Claude 4.7 Opus or Claude 5 Sonnet cheaper?

For a typical request (10,000 input + 2,000 output tokens), Claude 5 Sonnet is cheaper — about 60% less, or roughly $6000 saved per 100,000 requests. Claude 4.7 Opus runs $5/$25 per 1M input/output tokens; Claude 5 Sonnet runs $2/$10.

Which has the larger context window?

Both support a 1,000,000-token context window.

How accurate are these token counts?

Claude 4.7 Opus: Approximated with cl100k_base — drift typically <2% on English and code. Claude 5 Sonnet: Approximated with cl100k_base — drift typically <2% on English and code. The dollar math itself is exact once the token count is known.

Claude 4.7 Opus vs Claude 5 Sonnet: pricing & cost comparison

On input tokens, Claude 5 Sonnet is the cheaper of the two — 60% less per million ($5 vs $2). On output, Claude 5 Sonnet is 60% cheaper ($25 vs $10) — and since output is usually the dominant cost driver, that gap matters more than it looks.

Side by side

	Claude 4.7 Opus	Claude 5 Sonnet
Input / 1M tokens	$5	$2
Output / 1M tokens	$25	$10
Context window	1,000,000	1,000,000
Token-count accuracy	±2%	±2%
Cost — 10,000 input + 2,000 output tokens	$0.1	$0.04

What a real request costs

Take a representative turn — 10,000 input + 2,000 output tokens. Claude 4.7 Opus comes to $0.1, Claude 5 Sonnet to $0.04. Across 100,000 requests that's a $6000 swing in favour of Claude 5 Sonnet. To run the numbers on your actual prompt, paste it into the calculator and toggle Compare across all models.

Same vendor — an easy switch

Moving between Claude 4.7 Opus and Claude 5 Sonnet is a same-vendor move — one SDK, one tokenizer, so no recalibration. That makes this a straight cost/quality call: send the routine bulk of traffic to Claude 5 Sonnet ($2/$10 per 1M) and reserve Claude 4.7 Opus for the requests that visibly need its extra headroom. On the worked example above that split is worth about 60% per request — small per call, real money once you multiply by volume.

See the full breakdown on the dedicated pages for Claude 4.7 Opus and Claude 5 Sonnet.

FAQ

Is Claude 4.7 Opus or Claude 5 Sonnet cheaper?: For a typical request (10,000 input + 2,000 output tokens), Claude 5 Sonnet is cheaper — about 60% less, or roughly $6000 saved per 100,000 requests. Claude 4.7 Opus runs $5/$25 per 1M input/output tokens; Claude 5 Sonnet runs $2/$10.
Which has the larger context window?: Both support a 1,000,000-token context window.
How accurate are these token counts?: Claude 4.7 Opus: Approximated with cl100k_base — drift typically <2% on English and code. Claude 5 Sonnet: Approximated with cl100k_base — drift typically <2% on English and code. The dollar math itself is exact once the token count is known.

Both prices are computed from tokenmath's verified pricing table. Rates sourced from platform.claude.com, verified 2026-07-06. Vendor pricing changes often — confirm before you commit.