From b5296df8a934e8fec7cd3f0b2aa4b341ec8eab17 Mon Sep 17 00:00:00 2001 From: Alex Date: Mon, 21 Sep 2026 14:30:48 +0100 Subject: [PATCH] feat(pricing): cached-input rates for gpt-5.4-mini and gpt-5.4-nano Checked against OpenAI's pricing page: gpt-5.5 at $5 / $30 (cached $0.50) was already right. The mini and nano models declared no cached rate, so cached prompt tokens were billed at the full input rate. --- docsgpt/core/models/openai.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docsgpt/core/models/openai.yaml b/docsgpt/core/models/openai.yaml index 598e7b3c..a4b73a3a 100644 --- a/docsgpt/core/models/openai.yaml +++ b/docsgpt/core/models/openai.yaml @@ -12,6 +12,7 @@ models: context_window: 1050000 api_flavor: responses reasoning_effort: medium + # Short-context rates. Prompts over 272K tokens bill at $10 / $45 (cached $1). input_cost_per_million: 5.0 output_cost_per_million: 30.0 cached_input_cost_per_million: 0.5 @@ -20,8 +21,10 @@ models: description: Cost-efficient GPT-5.4-class model for high-volume coding, computer use, and subagent workloads input_cost_per_million: 0.75 output_cost_per_million: 4.5 + cached_input_cost_per_million: 0.075 - id: gpt-5.4-nano display_name: GPT-5.4 Nano description: Cheapest GPT-5.4-class model, optimized for simple high-volume tasks where speed and cost matter most input_cost_per_million: 0.2 output_cost_per_million: 1.25 + cached_input_cost_per_million: 0.02