mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-14 02:15:06 +00:00
Alex
1e14605ee7
- check_usage treats a request through a keyless (draft) agent as agent traffic, matching how its usage rows are bucketed and the headless rule - dashboard edits carry the stored enabled flag instead of re-enabling the policy; disabled policies are labelled in the Quotas tab and the editor - quota 429s send x-should-retry: false so OpenAI SDK clients do not retry a refusal that cannot succeed before the reset - cached-input and cache-write rates for Anthropic, OpenRouter and Groq gpt-oss-120b; refresh OpenRouter deepseek-v3.2 list prices - UsageQuota reuses usagePercent; docs note that a user override needs an existing user
36 lines
1.1 KiB
YAML
36 lines
1.1 KiB
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
|
|
cached_input_cost_per_million: 0.5
|
|
cache_write_cost_per_million: 6.25
|
|
|
|
- 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
|
|
cached_input_cost_per_million: 0.3
|
|
cache_write_cost_per_million: 3.75
|
|
|
|
- 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
|
|
cached_input_cost_per_million: 0.1
|
|
cache_write_cost_per_million: 1.25
|