wehub-resource-sync
26 lines
620 B
TOML
26 lines
620 B
TOML
# Source: https://routellm.abacus.ai/v1/models
|
|
# RouteLLM input_modalities: ['text', 'image', 'audio']
|
|
# RouteLLM output_modalities: ['text']
|
|
# RouteLLM context_length: 1048576
|
|
# RouteLLM max_completion_tokens: 65536
|
|
# RouteLLM input_token_rate: 0.00000025
|
|
# RouteLLM output_token_rate: 0.0000015
|
|
# RouteLLM cached_input_token_rate: 0.000000025
|
|
# RouteLLM thinking: True
|
|
base_model = "google/gemini-3.1-flash-lite"
|
|
reasoning = true
|
|
reasoning_options = []
|
|
|
|
[cost]
|
|
input = 0.25
|
|
output = 1.5
|
|
cache_read = 0.025
|
|
|
|
[limit]
|
|
context = 1_048_576
|
|
output = 65_536
|
|
|
|
[modalities]
|
|
input = ["text", "image", "audio"]
|
|
output = ["text"]
|