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
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Small Models Have Arrivedcalv.info
- Latency Scaling Differences for GPT and Claude Modelsepoch.ai
- Compare AI Models: Pricing, Context & Benchmarks | OpenRouteropenrouter.ai
- State of AI 2025: 100T Token LLM Usage Study | OpenRouteropenrouter.ai
- Pulse — Poolsidepoolside.ai
- AI Token Spend Management | Track Token Usage & Spend by Provider, Model, and User | Rampramp.com
- Introducing Claude Opus 4.7 \ Anthropicanthropic.com
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- A Picture is Worth 170 Tokens: How Does GPT-4o Encode Images?oranlooney.com
- Inference characteristics of Llama · Cursorcursor.com