mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-12 14:14:50 +00:00
Alex
b5296df8a9
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.
31 lines
1.1 KiB
YAML
31 lines
1.1 KiB
YAML
provider: openai
|
|
defaults:
|
|
supports_tools: true
|
|
supports_structured_output: true
|
|
attachments: [image]
|
|
context_window: 400000
|
|
|
|
models:
|
|
- id: gpt-5.5
|
|
display_name: GPT-5.5
|
|
description: Flagship frontier model for complex reasoning, coding, and agentic work with a 1M-token context window
|
|
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
|
|
- id: gpt-5.4-mini
|
|
display_name: GPT-5.4 Mini
|
|
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
|