Skip to content

Add Fireworks Kimi K2.5 Turbo router #1256

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

Merged
rekram1-node merged 1 commit into from
Mar 23, 2026
Merged

Add Fireworks Kimi K2.5 Turbo router #1256

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
26 changes: 26 additions & 0 deletions providers/fireworks-ai/models/accounts/fireworks/routers/kimi-k2p5-turbo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
name = "Kimi K2.5 Turbo"
family = "kimi-thinking"
release_date = "2026-01-27"
last_updated = "2026-01-27"
knowledge = "2025-01"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[cost]
cache_read = 0
input = 0
Comment on lines +12 to +14
Copy link
Copy Markdown
Collaborator

@rekram1-node rekram1-node Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's free?

Copy link
Copy Markdown
Collaborator

@rekram1-node rekram1-node Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh i see pr description hm

Copy link
Copy Markdown
Contributor Author

@jonathancaevans jonathancaevans Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@rekram1-node Pricing set to 0 (per-token costs absorbed by Fireworks' developer Pass subscription - follows precedent from other flat-rate providers like alibaba-coding-plan-cn)

Let me know if there's a better practice for indicating unique model id's for flat rate providers.

output = 0

[limit]
context = 256_000
output = 256_000

[modalities]
input = ["text", "image"]
output = ["text"]

[interleaved]
field = "reasoning_content"
Loading