# Cache write tokens now count on OpenAI and LiteLLM

> Agno's MessageMetrics.cache_write_tokens now carries the prompt cache writes that OpenAI Chat Completions, OpenAI Responses and LiteLLM report. Earlier releases left it at zero for all three.

- Published: 2026-10-08
- Author: Bas Nijholt
- Categories: Changelog
- Canonical: https://www.agno.com/blog/cache-write-tokens-now-count-on-openai-and-litellm
- Markdown: https://www.agno.com/blog/cache-write-tokens-now-count-on-openai-and-litellm.md

Agno's `OpenAIChat` fills `MessageMetrics.cache_write_tokens` from `usage.prompt_tokens_details.cache_write_tokens`, and `OpenAIResponses` from `usage.input_tokens_details.cache_write_tokens`. Both already read `cached_tokens` from the same object into `cache_read_tokens`, so a run now shows both sides of the prompt cache.

The `LiteLLM` model reads `prompt_tokens_details.cache_write_tokens` and falls back to `cache_creation_tokens`, the mirror LiteLLM also fills. That covers Claude and any other cache-writing provider behind LiteLLM, whether the usage arrives as a dict or as LiteLLM's `Usage` object. A missing or null field still counts as zero, and the value adds up into run and session metrics like every other token count.

We passed each parser a usage payload built with the provider SDK's own types: 3,000 written tokens for the two OpenAI APIs, and LiteLLM's `Usage` with `cache_creation_tokens=4000`.

```text
# Before (real output)
OpenAIChat       cache_read_tokens=12000  cache_write_tokens=0
OpenAIResponses  cache_read_tokens=12000  cache_write_tokens=0
LiteLLM          cache_read_tokens=8000   cache_write_tokens=0

# Now (real output)
OpenAIChat       cache_read_tokens=12000  cache_write_tokens=3000
OpenAIResponses  cache_read_tokens=12000  cache_write_tokens=3000
LiteLLM          cache_read_tokens=8000   cache_write_tokens=4000
```

Learn more about [cache and reasoning token metrics](https://docs.agno.com/sessions/metrics/usage/agent-extra-metrics) and [LiteLLM](https://docs.agno.com/models/providers/gateways/litellm/overview) in the documentation.