Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 3 additions & 0 deletions deploy/config/llmhubs/gpt5.4-template.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,9 @@ provider_template_type: azure_openai
config:
deployment_name: gpt-5.4
endpoint: https://YOUR-RESOURCE.cognitiveservices.azure.com/
# Auth: set AZURE_OPENAI_API_KEY for key-based auth. Leave the env var unset
# to fall back to Azure managed identity (DefaultAzureCredential).
api_key: ${AZURE_OPENAI_API_KEY:-}
api_version: preview
timeout_ms: 60000
max_tokens: 128000
Expand Down
9 changes: 9 additions & 0 deletions deploy/config/llmhubs/model-template.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ io_profile:
# config:
# endpoint: https://example.cognitiveservices.azure.com/
# deployment_name: gpt-5.4
# api_key: ${AZURE_OPENAI_API_KEY:-} # key auth; leave env unset for managed identity
# api_version: preview # v1 API — no api-version in URL
# unsupported_request_options: [] # Optional: drop request options the model rejects
# timeout_ms: 60000
Expand All @@ -51,6 +52,7 @@ io_profile:
# config:
# endpoint: https://example.services.ai.azure.com/openai/v1
# deployment_name: DeepSeek-V3.2
# api_key: ${AZURE_OPENAI_API_KEY:-} # key auth; leave env unset for managed identity
# api_version: preview
# use_chat_completions: true # stay on Chat Completions
# unsupported_request_options: [] # Optional: drop request options the model rejects
Expand All @@ -63,6 +65,7 @@ io_profile:
# base_url: https://api.deepseek.com
# path: /chat/completions
# upstream_model_name: deepseek-reasoner
# bearer_token: ${DEEPSEEK_API_KEY} # sent as Authorization: Bearer <token>
# use_chat_completions: true # Optional: force Chat Completions for this model
# use_responses_api: true # Optional: force Responses API when request shape is supported
# passthrough_options: [] # Optional: allow specific request.options keys for all request types
Expand All @@ -81,6 +84,7 @@ io_profile:
# config:
# base_url: https://openrouter.ai/api/v1
# upstream_model_name: anthropic/claude-sonnet-4
# bearer_token: ${OPENROUTER_API_KEY} # sent as Authorization: Bearer <token>
# use_responses_api: true # Optional: enable /responses for OpenRouter
# site_url: https://example.com # Optional: sent as HTTP-Referer unless default_headers already sets it
# app_name: Sico # Optional: sent as X-OpenRouter-Title unless default_headers already sets it
Expand All @@ -91,13 +95,15 @@ io_profile:
# config:
# base_url: https://api.anthropic.com
# upstream_model_name: claude-sonnet-4-20250514
# api_key_value: ${ANTHROPIC_API_KEY} # sent as x-api-key header
# timeout_ms: 60000
# max_tokens: 4096
#
# Gemini (provider_template_type: gemini):
# config:
# base_url: https://generativelanguage.googleapis.com
# upstream_model_name: gemini-2.5-flash
# api_key_value: ${GEMINI_API_KEY} # API key for Gemini
# timeout_ms: 60000
# max_tokens: 4096
#
Expand Down Expand Up @@ -132,6 +138,9 @@ io_profile:
config:
deployment_name: your-deployment-name
endpoint: https://example.openai.azure.com/
# Auth: set AZURE_OPENAI_API_KEY for key-based auth. Leave the env var unset
# to fall back to Azure managed identity (DefaultAzureCredential).
api_key: ${AZURE_OPENAI_API_KEY:-}
api_version: preview
timeout_ms: 60000
max_tokens: 4096
Loading