50 lines
1.0 KiB
TOML
50 lines
1.0 KiB
TOML
# Venice.ai — https://venice.ai
|
|
# Models: 3
|
|
|
|
[provider]
|
|
id = "venice"
|
|
display_name = "Venice.ai"
|
|
api_key_env = "VENICE_API_KEY"
|
|
base_url = "https://api.venice.ai/api/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "venice-uncensored"
|
|
display_name = "Venice Uncensored"
|
|
tier = "fast"
|
|
context_window = 32000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.20
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["venice"]
|
|
|
|
[[models]]
|
|
id = "llama-3.3-70b"
|
|
display_name = "Llama 3.3 70B (Venice)"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.32
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen3-235b-a22b-instruct-2507"
|
|
display_name = "Qwen3 235B A22B (Venice)"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.20
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|