Skip to content

feat(llm): add openrouter backend support with configurable API and model options #1041

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
the-cybersapien wants to merge 2 commits into
base: v8
Choose a base branch
from
+13 −0
Open

feat(llm): add openrouter backend support with configurable API and model options #1041

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
079ff45
feat: add OpenRouter backend support with configurable API and model …
the-cybersapien May 27, 2026
1bd3fc0
chore(llm): add pricing and fix comments
the-cybersapien May 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions graphify/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,19 @@ def _get_tokenizer():
"temperature": 0,
"max_tokens": 16384,
},
"openrouter": {
# Routes through OpenRouter's OpenAI-compatible API proxy, which can connect to various backends including Kimi and Gemini.
# Default model is set to qwen/qwen3.6-flash as it's a cheap and well-performing model with low latency, and
# is widely accessible via OpenRouter, but users can override with any model supported by their OpenRouter account.
"base_url": "https://openrouter.ai/api/v1",
"default_model": "qwen/qwen3.6-flash",
"env_keys": ["OPENROUTER_API_KEY"],
"model_env_key": "GRAPHIFY_OPENROUTER_MODEL",
# Pricing set for default model, others may be different
"pricing": {"input": 0.1875, "output": 1.125},
"temperature": 0,
"max_tokens": 16384,
},
}


Expand Down