Claude Sonnet 5 pricing for marketing copy

Quick start

Call Claude Sonnet 5 with the Anthropic Python SDK:

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=3000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.0316 per call at standard rates
# Input:  $2.00/MTok
# Output: $10.00/MTok

How Claude Sonnet 5 compares on cost

Per-call cost for all models scoring 50+ on marketing copy benchmarks. Hover for details.

Cheapest viable option: GPT 5.6 Terra at $0.0376/call (-19% less, 80/100 quality).

What drives marketing copy cost

Marketing copy is generated in variants (the same brief producing many versions for testing), so cost scales with variant count rather than brief length. Requesting several variants in one call is markedly cheaper than several calls, because the brief and brand context are sent once instead of repeatedly.

For Claude Sonnet 5 specifically, that means output tokens cost 5.0x more than input, at $10.00 vs $2.00 per MTok. At this use case’s 800/3,000 token split, output accounts for 95% of the $0.0316 per-call cost.

Claude Sonnet 5 quality benchmarks for marketing copy

Performance across all task types

Claude Sonnet 5 scores by task type. Marketing Copy highlighted.

Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.

About Claude Sonnet 5

Launched at $2/$10 as introductory pricing through Aug 31, 2026. Anthropic cancelled the scheduled increase to $3/$15, so this is now the standard price.

Other models from Claude

You can compare Claude Sonnet 5 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions