mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-18 16:13:19 +00:00
Alex
b77561288d
Rename the unused *_cost_per_token capability fields to USD per 1M tokens, add prompt-cache read/write rates, and ship list prices for the hosted catalogs. The old per-token keys still load, scaled, with a warning. docsgpt/pricing.py turns a call's token bins into a USD cost. Models with no declared rate cost $0 unless QUOTA_UNPRICED_RATE_PER_MILLION is set.
30 lines
894 B
YAML
30 lines
894 B
YAML
provider: anthropic
|
|
defaults:
|
|
supports_tools: true
|
|
attachments: [image, pdf]
|
|
context_window: 200000
|
|
|
|
models:
|
|
- id: claude-opus-4-7
|
|
display_name: Claude Opus 4.7
|
|
description: Most capable Claude model for complex reasoning and agentic coding
|
|
context_window: 1000000
|
|
supports_structured_output: true
|
|
input_cost_per_million: 5.0
|
|
output_cost_per_million: 25.0
|
|
|
|
- id: claude-sonnet-4-6
|
|
display_name: Claude Sonnet 4.6
|
|
description: Best balance of speed and intelligence with extended thinking
|
|
context_window: 1000000
|
|
supports_structured_output: true
|
|
input_cost_per_million: 3.0
|
|
output_cost_per_million: 15.0
|
|
|
|
- id: claude-haiku-4-5
|
|
display_name: Claude Haiku 4.5
|
|
description: Fastest Claude model with near-frontier intelligence
|
|
supports_structured_output: true
|
|
input_cost_per_million: 1.0
|
|
output_cost_per_million: 5.0
|