Evan
21c82e335c
Community-maintained TOML catalog for LibreFang. New models can be added via PR without requiring a LibreFang binary release. Includes validation script, bilingual docs, and GitHub templates.
75 lines
1.7 KiB
TOML
75 lines
1.7 KiB
TOML
# Fireworks AI — https://fireworks.ai
|
|
# Models: 5
|
|
|
|
[provider]
|
|
id = "fireworks"
|
|
display_name = "Fireworks AI"
|
|
api_key_env = "FIREWORKS_API_KEY"
|
|
base_url = "https://api.fireworks.ai/inference/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "accounts/fireworks/models/llama-v3p1-405b-instruct"
|
|
display_name = "Llama 3.1 405B (Fireworks)"
|
|
tier = "frontier"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 3.00
|
|
output_cost_per_m = 3.00
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "accounts/fireworks/models/llama-v3p3-70b-instruct"
|
|
display_name = "Llama 3.3 70B (Fireworks)"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.90
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "accounts/fireworks/models/deepseek-r1"
|
|
display_name = "DeepSeek R1 (Fireworks)"
|
|
tier = "frontier"
|
|
context_window = 64000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 3.00
|
|
output_cost_per_m = 8.00
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "accounts/fireworks/models/deepseek-v3"
|
|
display_name = "DeepSeek V3 (Fireworks)"
|
|
tier = "smart"
|
|
context_window = 64000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.90
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "accounts/fireworks/models/mixtral-8x22b-instruct"
|
|
display_name = "Mixtral 8x22B (Fireworks)"
|
|
tier = "balanced"
|
|
context_window = 65536
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.90
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|