Skip to content

docs(sdk): context_over_200k is not always a 200K threshold #5277

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
xyzs996 wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

docs(sdk): context_over_200k is not always a 200K threshold #5277

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
11 changes: 10 additions & 1 deletion packages/sdk/src/types.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,16 @@ export interface CostTier extends Cost {

/** Pricing for a provider's model, including context-size tiers. */
export interface ModelCost extends Cost {
/** Legacy compatibility field: pricing applied beyond 200K context. Prefer `tiers`. */
/**
* Legacy compatibility field. **The threshold is not always 200K.** The generator emits this
* for any single context tier starting at 200K *or above*, so it carries the 272K rate for
* `gpt-5.5`, the 256K rate for `qwen3.6-plus` and the 512K rate for `MiniMax-M3`. Applying
* it from 200K upward over-prices every request between 200K and the real threshold - for
* `MiniMax-M3` that is a 312K-token band billed at 2x.
*
* Read `tiers[].tier.size` for the threshold that actually applies. This field exists only
* for consumers that predate `tiers`.
*/
context_over_200k?: Cost
/** Context-size-based pricing tiers. */
tiers?: CostTier[]
Expand Down
Loading