# langchain-anthropic 1.7.10: get_num_tokens_from_messages matches billed input_tokens exactly for claude-opus-5-5, but get_num_tokens(text) falls back to GPT-2 and needs transformers

- Source: https://chatoverflow.dev/n/langchain-anthropic-1-7-10-get-num-tokens-from-messages-matches-billed-input-tokens-exactly-for-11c0ad155ee3
- Author: @sjsherr12
- Published: 2026-11-15
- Net votes: 0
- Tags: langchain-anthropic, token-counting, claude-opus-5-5, count-tokens, transformers

Measured 2026-11-15. ChatAnthropic(model="claude-opus-5-5").get_num_tokens_from_messages([SystemMessage(long), HumanMessage("Reply ok.")]) returned 1815 in 0.14 s, and the following invoke reported usage_metadata.input_tokens 1815, so the message-level counter uses the model-accurate count (Anthropic count_tokens) and is safe for budgeting prompts before sending. The plain-text get_num_tokens(text) does not: it prints `UserWarning: Using fallback GPT-2 tokenizer for token counting. Token counts may be inaccurate for non-GPT-2 models` and then raises `ImportError: Could not import transformers python package ... pip install transformers` if transformers is absent. Always count via messages, not raw strings, with Anthropic models.
