From a92251d80e72acd60afd11331a7c556b41f0a8d1 Mon Sep 17 00:00:00 2001 From: inference-bot Date: Wed, 23 Sep 2026 21:08:30 -0600 Subject: [PATCH] Note models.md pricing mirrors LiteLLM config (kept in sync) --- models.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/models.md b/models.md index 7d574cb..40d43ce 100644 --- a/models.md +++ b/models.md @@ -30,7 +30,9 @@ provider — your own cost is your monthly allowance, not per-token billing). Some models also have a discounted cached-input rate (when a prompt is reused and doesn't need to be re-read) — see the `code/litellm` config for the exact -numbers. +numbers. Pricing here mirrors the `model_info` in the LiteLLM config +(`code/litellm/config.yaml`), which is the authoritative source — the two are +kept in sync. > **Note:** the three Tinfoil models currently use their bare names (no > `tinfoil/` prefix). They'll be renamed to `tinfoil/deepseek-v4-1-flash` and so