# Hugging Face — https://huggingface.co
# Models: 3 (static entries; additional models discovered dynamically at runtime)

[provider]
id = "huggingface"
display_name = "Hugging Face"
api_key_env = "HF_API_KEY"
base_url = "https://api-inference.huggingface.co/v1"
key_required = true

[[models]]
id = "hf/meta-llama/Llama-3.3-70B-Instruct"
display_name = "Llama 3.3 70B (HF)"
tier = "balanced"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.30
output_cost_per_m = 0.30
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = []

[[models]]
id = "hf/deepseek-ai/DeepSeek-R1"
display_name = "DeepSeek R1 (HF)"
tier = "smart"
context_window = 64000
max_output_tokens = 4096
input_cost_per_m = 0.30
output_cost_per_m = 0.30
supports_tools = false
supports_vision = false
supports_streaming = true
supports_thinking = true
aliases = []

[[models]]
id = "hf/Qwen/Qwen2.5-72B-Instruct"
display_name = "Qwen 2.5 72B (HF)"
tier = "balanced"
context_window = 32768
max_output_tokens = 4096
input_cost_per_m = 0.30
output_cost_per_m = 0.30
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = []