[provider]
id = "vertex-ai"
display_name = "Google Cloud Vertex AI"
# Points to a service-account JSON file path, not a raw API key.
api_key_env = "GOOGLE_APPLICATION_CREDENTIALS"
base_url = "https://us-central1-aiplatform.googleapis.com"
key_required = true

[[models]]
id = "vertex-ai/gemini-2.5-pro"
display_name = "Gemini 2.5 Pro (Vertex AI)"
provider = "vertex-ai"
tier = "frontier"
context_window = 1048576
max_output_tokens = 65536
input_cost_per_m = 1.25
output_cost_per_m = 10.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []

[[models]]
id = "vertex-ai/gemini-2.5-flash"
display_name = "Gemini 2.5 Flash (Vertex AI)"
provider = "vertex-ai"
tier = "smart"
context_window = 1048576
max_output_tokens = 65536
input_cost_per_m = 0.15
output_cost_per_m = 0.6
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []

[[models]]
id = "vertex-ai/gemini-2.0-flash"
display_name = "Gemini 2.0 Flash (Vertex AI)"
provider = "vertex-ai"
tier = "fast"
context_window = 1048576
max_output_tokens = 8192
input_cost_per_m = 0.1
output_cost_per_m = 0.4
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []

[[models]]
id = "vertex-ai/gemini-2.0-flash-lite"
display_name = "Gemini 2.0 Flash Lite (Vertex AI)"
provider = "vertex-ai"
tier = "fast"
context_window = 1048576
max_output_tokens = 8192
input_cost_per_m = 0.075
output_cost_per_m = 0.3
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []