configure litellm models

This commit is contained in:
Roger Oriol
2026-07-14 21:45:18 +02:00
parent cf6e2784fe
commit 279cc1f235

View File

@@ -27,11 +27,11 @@ data:
litellm_params: litellm_params:
model: gemini/gemini-3-flash-preview model: gemini/gemini-3-flash-preview
api_key: "os.environ/GEMINI_API_KEY" api_key: "os.environ/GEMINI_API_KEY"
- model_name: hy3 - model_name: tencent/hy3:free
litellm_params: litellm_params:
model: openrouter/tencent/hy3:free model: openrouter/tencent/hy3:free
api_key: "os.environ/OPENROUTER_API_KEY" api_key: "os.environ/OPENROUTER_API_KEY"
- model_name: glm-5.2 - model_name: z-ai/glm-5.2
litellm_params: litellm_params:
model: openrouter/z-ai/glm-5.2 model: openrouter/z-ai/glm-5.2
api_key: "os.environ/OPENROUTER_API_KEY" api_key: "os.environ/OPENROUTER_API_KEY"
@@ -39,10 +39,6 @@ data:
litellm_params: litellm_params:
model: ollama/glm-4.7-flash model: ollama/glm-4.7-flash
api_base: http://10.88.20.12:11434 api_base: http://10.88.20.12:11434
- model_name: qwen-3.6
litellm_params:
model: ollama/qwen-3.6
api_base: http://10.88.20.12:11434
# Used by the platform-engineer Hermes agent (deployed in ns platform-engineer). # Used by the platform-engineer Hermes agent (deployed in ns platform-engineer).
# model_name is the alias Hermes requests; the underlying Ollama model is # model_name is the alias Hermes requests; the underlying Ollama model is
# qwen3.6:latest (the fast non-27b tag). 27b is a slow reasoning model. # qwen3.6:latest (the fast non-27b tag). 27b is a slow reasoning model.