# DeepInfra — https://deepinfra.com
# Serverless open-model inference (Llama, Mistral, Qwen, etc.)

[provider]
id = "deepinfra"
display_name = "DeepInfra"
api_key_env = "DEEPINFRA_API_KEY"
base_url = "https://api.deepinfra.com/v1/openai"
key_required = true

[[models]]
id = "Qwen/Qwen2.5-72B-Instruct"
display_name = "Qwen 2.5 72B Instruct"
tier = "balanced"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.35
output_cost_per_m = 0.4
supports_tools = true
supports_vision = false
supports_streaming = true