wehub-resource-sync
20 lines
473 B
TOML
20 lines
473 B
TOML
# This model is restricted here to $.reasoning_effort or $.reasoning.effort
|
|
# = "low"|"medium"|"high"; no exact token budget is documented for it.
|
|
# https://docs.llmgateway.io/features/reasoning (accessed 2026-06-25)
|
|
base_model = "xai/grok-4.3"
|
|
|
|
[[reasoning_options]]
|
|
type = "effort"
|
|
values = ["low", "medium", "high"]
|
|
|
|
[cost]
|
|
input = 1.25
|
|
output = 2.5
|
|
cache_read = 0.3125
|
|
|
|
[[cost.tiers]]
|
|
tier = { type = "context", size = 200_000 }
|
|
input = 2.5
|
|
output = 5
|
|
cache_read = 0.4
|