50 lines
1.0 KiB
TOML
50 lines
1.0 KiB
TOML
# meta-llama — https://llama.com
|
|
# Models: 5
|
|
|
|
[provider]
|
|
id = "meta-llama"
|
|
display_name = "Meta Llama"
|
|
api_key_env = "LLAMA_API_KEY"
|
|
base_url = "https://api.llama.com/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "llama-4-maverick"
|
|
display_name = "Meta: Llama 4 Maverick"
|
|
tier = "fast"
|
|
context_window = 1048576
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.6
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-4-scout"
|
|
display_name = "Meta: Llama 4 Scout"
|
|
tier = "fast"
|
|
context_window = 327680
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.08
|
|
output_cost_per_m = 0.3
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.3-70b-instruct"
|
|
display_name = "Meta: Llama 3.3 70B Instruct"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.32
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-guard-4-12b"
|
|
display_name = "Meta: Llama Guard 4 12B"
|
|
tier = "fast"
|
|
context_window = 163840
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.18
|
|
output_cost_per_m = 0.18
|
|
supports_streaming = true
|