mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-13 00:14:02 +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
35 lines
1.1 KiB
YAML
35 lines
1.1 KiB
YAML
provider: openrouter
|
|
defaults:
|
|
supports_tools: true
|
|
attachments: [image]
|
|
context_window: 128000
|
|
|
|
models:
|
|
- id: qwen/qwen3-coder:free
|
|
display_name: Qwen3 Coder (free)
|
|
description: Free-tier 480B MoE coder model with strong agentic tool use; rate-limited
|
|
context_window: 262000
|
|
attachments: []
|
|
input_cost_per_million: 0.0
|
|
output_cost_per_million: 0.0
|
|
|
|
- id: deepseek/deepseek-v3.2
|
|
display_name: DeepSeek V3.2
|
|
description: Open-weights reasoning model, very low cost (~$0.27 in / $0.40 out per 1M)
|
|
context_window: 131072
|
|
attachments: []
|
|
supports_structured_output: true
|
|
input_cost_per_million: 0.269
|
|
output_cost_per_million: 0.4
|
|
cached_input_cost_per_million: 0.1345
|
|
|
|
- id: anthropic/claude-sonnet-4.6
|
|
display_name: Claude Sonnet 4.6 (via OpenRouter)
|
|
description: Frontier Sonnet-class model with 1M context, vision, and 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
|