wehub-resource-sync
25 lines
520 B
TOML
25 lines
520 B
TOML
# Gateway-wide $.reasoning_effort = "none" disables non-OpenAI reasoning;
|
|
# this model has no documented effort tiers or exact reasoning-token budget.
|
|
# https://docs.llmgateway.io/features/reasoning (accessed 2026-06-25)
|
|
base_model = "xiaomi/mimo-v2.5"
|
|
|
|
[[reasoning_options]]
|
|
type = "toggle"
|
|
|
|
[interleaved]
|
|
field = "reasoning_content"
|
|
|
|
[cost]
|
|
input = 0.14
|
|
output = 0.28
|
|
cache_read = 0.0028
|
|
|
|
[[cost.tiers]]
|
|
tier = { type = "context", size = 256_000 }
|
|
input = 0.8
|
|
output = 4
|
|
cache_read = 0.16
|
|
|
|
[limit]
|
|
context = 1_000_000
|