Skip to content

kimi-for-coding: inherit indicative costs from base models instead of zeroing #4071

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lorecanc wants to merge 1 commit into
base: dev
Choose a base branch
from
+12 −26
Open

kimi-for-coding: inherit indicative costs from base models instead of zeroing #4071

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 3 additions & 7 deletions providers/kimi-for-coding/models/k3-256k.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,9 @@
# endpoint. Unlike full K3 it accepts no video input (image only).
# reasoning_options per the Kimi Code docs:
# reasoning_effort = "low" | "high" | "max" (default "high")
# Cost is zeroed per this provider's subscription convention.
# Kimi For Coding is a fixed-fee subscription plan. The cost is inherited
# from the base model and is the *indicative* pay-per-token equivalent, for
# usage tracking only, not the actual billing rate.
base_model = "moonshotai/kimi-k3"
name = "Kimi K3-256K"
description = "256K-context version of Kimi K3, reducing token consumption for shorter coding sessions"
Expand All @@ -12,12 +14,6 @@ attachment = false
type = "effort"
values = ["low", "high", "max"]

[cost]
input = 0
output = 0
cache_read = 0
cache_write = 0

[limit]
context = 262_144

Expand Down
10 changes: 3 additions & 7 deletions providers/kimi-for-coding/models/k3.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
# reasoning_options mirror the Moonshot AI platform API surface:
# thinking.type = "enabled" | "disabled" | "adaptive"
# output_config.effort = "low" | "high" | "max"
# Cost is zeroed per this provider's subscription convention.
# Kimi For Coding is a fixed-fee subscription plan. The cost is inherited
# from the base model and is the *indicative* pay-per-token equivalent, for
# usage tracking only, not the actual billing rate.
base_model = "moonshotai/kimi-k3"
attachment = false

Expand All @@ -11,9 +13,3 @@ type = "toggle"
[[reasoning_options]]
type = "effort"
values = ["low", "high", "max"]

[cost]
input = 0
output = 0
cache_read = 0
cache_write = 0
9 changes: 3 additions & 6 deletions providers/kimi-for-coding/models/kimi-for-coding-highspeed.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,9 @@
# Kimi For Coding is a fixed-fee subscription plan. The cost is inherited
# from the base model and is the *indicative* pay-per-token equivalent, for
# usage tracking only, not the actual billing rate.
base_model = "moonshotai/kimi-k2.7-code-highspeed"
name = "Kimi For Coding HighSpeed"
reasoning_options = []

[cost]
input = 0
output = 0
cache_read = 0
cache_write = 0

[limit]
output = 32_768
9 changes: 3 additions & 6 deletions providers/kimi-for-coding/models/kimi-for-coding.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,8 @@
# Kimi For Coding is a fixed-fee subscription plan. The cost is inherited
# from the base model and is the *indicative* pay-per-token equivalent, for
# usage tracking only, not the actual billing rate.
base_model = "moonshotai/kimi-k2.7-code"
reasoning_options = []

[cost]
input = 0
output = 0
cache_read = 0
cache_write = 0

[limit]
output = 32_768
Loading