Opus 4.7's New Tokenizer: What It Actually Costs — OpenRouter Blog
openrouter.ai · 1,100 words · saved by 1 readers
Anthropic changed the tokenizer in Opus 4.7. We looked at usage that shifted from 4.6 to 4.7 to measure exactly how it affects costs.
Opus 4.7's New Tokenizer: What It Actually Costs Justin Summerville · 4/27/2026 We Used Our Own Tokenizer to Get a Comparable Baseline We Used Our Own Tokenizer to Get a Comparable Baseline Opus 4.7 Produces 32–45% More Native Tokens Caching Absorbs Most of the Token Inflation Completion Length in Opus 4.7 Diverges Based on the Prompt Size Actual Cost Impact Methodology Anthropic announced that Claude Opus 4.7 improves the model’s understanding of inputs with a new tokenizer. This means that while the model price hasn’t changed ($5/M input, $25/M output), the same inputs will cost more
saved by
related reading
- Introducing Claude Opus 4.7 \ Anthropicanthropic.com
- Two different tricks for fast LLM inferenceseangoedecke.com
- State of AI 2025: 100T Token LLM Usage Study | OpenRouteropenrouter.ai
- A Picture is Worth 170 Tokens: How Does GPT-4o Encode Images?oranlooney.com
- I think Anthropic and OpenAI have found product-market fitsimonwillison.net
- Compare AI Models: Pricing, Context & Benchmarks | OpenRouteropenrouter.ai
- Latency Scaling Differences for GPT and Claude Modelsepoch.ai
- openai burns the boatsethanding.substack.com
- Recent LLMs can use filler tokens or problem repeats to improve (no-CoT) math performanceblog.redwoodresearch.org
- Opus 4.7 Part 2: Capabilities and Reactionsthezvi.substack.com
- The Supply and Demand of AI Tokens | Dylan Patel Interviewyoutube.com
- Claude Opus 4.5: Model Card, Alignment and Safetythezvi.substack.com