Evan
c192f493b4
Providers with known public APIs use their official endpoints: - meta-llama → api.llama.com/v1 - microsoft → models.inference.ai.azure.com (GitHub Models) - ibm-granite → us-south.ml.cloud.ibm.com/ml/v1 (watsonx) - tencent → api.hunyuan.cloud.tencent.com/v1 - morph → api.morphllm.com/v1 16 remaining providers without known public APIs route through OpenRouter (base_url = openrouter.ai/api/v1, OPENROUTER_API_KEY). sync-pricing.py updated with PROVIDER_API mapping.
149 lines
3.2 KiB
TOML
149 lines
3.2 KiB
TOML
# meta-llama — auto-generated from OpenRouter API
|
|
|
|
[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-3-70b-instruct"
|
|
display_name = "Meta: Llama 3 70B Instruct"
|
|
tier = "smart"
|
|
context_window = 8192
|
|
max_output_tokens = 8000
|
|
input_cost_per_m = 0.51
|
|
output_cost_per_m = 0.74
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3-8b-instruct"
|
|
display_name = "Meta: Llama 3 8B Instruct"
|
|
tier = "fast"
|
|
context_window = 8192
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.03
|
|
output_cost_per_m = 0.04
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.1-70b-instruct"
|
|
display_name = "Meta: Llama 3.1 70B Instruct"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.4
|
|
output_cost_per_m = 0.4
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.1-8b-instruct"
|
|
display_name = "Meta: Llama 3.1 8B Instruct"
|
|
tier = "fast"
|
|
context_window = 16384
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.02
|
|
output_cost_per_m = 0.05
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.2-11b-vision-instruct"
|
|
display_name = "Meta: Llama 3.2 11B Vision Instruct"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.049
|
|
output_cost_per_m = 0.049
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.2-1b-instruct"
|
|
display_name = "Meta: Llama 3.2 1B Instruct"
|
|
tier = "fast"
|
|
context_window = 60000
|
|
max_output_tokens = 15000
|
|
input_cost_per_m = 0.027
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.2-3b-instruct"
|
|
display_name = "Meta: Llama 3.2 3B Instruct"
|
|
tier = "fast"
|
|
context_window = 80000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.051
|
|
output_cost_per_m = 0.34
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.2-3b-instruct:free"
|
|
display_name = "Meta: Llama 3.2 3B Instruct (free)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
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-3.3-70b-instruct:free"
|
|
display_name = "Meta: Llama 3.3 70B Instruct (free)"
|
|
tier = "fast"
|
|
context_window = 65536
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = 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-guard-3-8b"
|
|
display_name = "Llama Guard 3 8B"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.02
|
|
output_cost_per_m = 0.06
|
|
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
|