wehub-resource-sync
16 lines
495 B
TOML
16 lines
495 B
TOML
# Native `/ai/run` accepts `reasoning_effort = low|medium|high` and
|
|
# `chat_template_kwargs.enable_thinking = true|false`; no budget is documented.
|
|
# https://developers.cloudflare.com/workers-ai/models/gemma-4-26b-a4b-it/sync-input.json (accessed 2026-06-25)
|
|
|
|
base_model = "google/gemma-4-26b-a4b-it"
|
|
reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["low", "medium", "high"] }]
|
|
interleaved = true
|
|
|
|
[cost]
|
|
input = 0.1
|
|
output = 0.3
|
|
|
|
[limit]
|
|
context = 256_000
|
|
output = 16_384
|