# 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 = "meta-llama/Meta-Llama-3.1-8B-Instruct"
display_name = "Llama 3.1 8B Instruct"
tier = "fast"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.06
output_cost_per_m = 0.06
supports_tools = true
supports_vision = false
supports_streaming = true

[[models]]
id = "meta-llama/Meta-Llama-3.1-70B-Instruct"
display_name = "Llama 3.1 70B Instruct"
tier = "balanced"
context_window = 128000
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

[[models]]
id = "meta-llama/Meta-Llama-3.1-405B-Instruct"
display_name = "Llama 3.1 405B Instruct"
tier = "smart"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.8
output_cost_per_m = 0.8
supports_tools = true
supports_vision = false
supports_streaming = true

[[models]]
id = "mistralai/Mistral-7B-Instruct-v0.3"
display_name = "Mistral 7B Instruct v0.3"
tier = "fast"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.07
output_cost_per_m = 0.07
supports_tools = true
supports_vision = false
supports_streaming = 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