// claude
Claude Opus 4.7
Anthropic's flagship reasoning model — the coding and agent workhorse.
Previous generation
Claude Opus 4.7 still runs on llmrelay at the rates below, and we keep selling it — pinned versions matter when you have output you do not want to re-validate. For new work, Claude Opus 5 is the current pick at $2.5/M input.
Official list
llmrelay
Input / M tokens
$5.00
$2.50
Output / M tokens
$25.00
$12.50
Context window
—
1,000,000 tokens
Max output
—
128,000 tokens
What it costs you per month
Real-world budget scenarios. Numbers are simple sums — official list price vs llmrelay's 50% off tier.
Usage scenario
Official
llmrelay
Light coding (1M in / 200K out per month)
$10.00
$5.00save $5.00
Heavy Cursor / Cline user (50M in / 5M out per month)
$375.00
$187.50save $187.50
Production RAG (500M in / 20M out per month)
$3000.00
$1500.00save $1500.00
What it's good at
- +SWE-bench leader
- +Complex multi-file refactors
- +Long agent trajectories
- +Tool use
Best for
- — Cursor / Cline / Roo Code heavy users
- — Agent frameworks
- — Codebase-scale reasoning
Try Claude Opus 4.7 at half the price
Free to create an account, no subscription, $10 minimum top-up — enough to run this model against a real task and judge quality yourself.
Get API key →