Opus 4.7 Tokenizer
- Entity ID:
ent-20260423-r30a00000000f - Type:
mechanism - Scope:
private - Status:
active
Description
New tokenizer shipped with Opus 4.7 that produces 1.0-1.35x more tokens than Opus 4.6 for identical text. English-heavy prose sits near ~1.1x; code-heavy prompts with long identifiers, generics, and nested constructs can hit ~1.35x. Per-token pricing unchanged, so worst-case effective cost rises ~35%. Interacts with prompt caching: cache-friendly workflows can partially absorb the overhead; cache-hostile workflows just pay more.
Key claims
- Opus 4.7 tokenizer produces 1.0-1.35x more tokens per text
- Cache-friendly workflows partially absorb 4.7 tokenizer overhead
- Opus 4.7 hits autocompact threshold earlier because of the new tokenizer
- xhigh + 1.35x tokenizer + bad cache = 2-3x cost vs 4.6 high
Relations
- Opus 4.7 Tokenizer --[contains]--> Claude Opus 4.7
- Tokenizer-Effort-Cache Cost-Multiplier Model --[depends_on]--> Opus 4.7 Tokenizer