mirror of
https://github.com/openclaw/openclaw.git
synced 2026-03-12 15:30:39 +00:00
fix: correct MiniMax M2.5 pricing (was ~50x too high) (openclaw#22755) thanks @miloudbelarebia
Verified: - pnpm build - pnpm check - pnpm test:macmini Co-authored-by: miloudbelarebia <136994453+miloudbelarebia@users.noreply.github.com> Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
This commit is contained in:
@@ -46,6 +46,7 @@ Docs: https://docs.openclaw.ai
|
||||
- Providers/Copilot: add `claude-sonnet-4.6` and `claude-sonnet-4.5` to the default GitHub Copilot model catalog and add coverage for model-list/definition helpers. (#20270, fixes #20091) Thanks @Clawborn.
|
||||
- Auto-reply/WebChat: avoid defaulting inbound runtime channel labels to unrelated providers (for example `whatsapp`) for webchat sessions so channel-specific formatting guidance stays accurate. (#21534) Thanks @lbo728.
|
||||
- Status: include persisted `cacheRead`/`cacheWrite` in session summaries so compact `/status` output consistently shows cache hit percentages from real session data.
|
||||
- Models/MiniMax: correct default M2.5 API pricing for input/output/cache token costs in onboarding and provider config defaults, fixing inflated usage cost reporting. (#21792)
|
||||
- Heartbeat/Cron: restore interval heartbeat behavior so missing `HEARTBEAT.md` no longer suppresses runs (only effectively empty files skip), preserving prompt-driven and tagged-cron execution paths.
|
||||
- WhatsApp/Cron/Heartbeat: enforce allowlisted routing for implicit scheduled/system delivery by merging pairing-store + configured `allowFrom` recipients, selecting authorized recipients when last-route context points to a non-allowlisted chat, and preventing heartbeat fan-out to recent unauthorized chats.
|
||||
- Heartbeat/Active hours: constrain active-hours `24` sentinel parsing to `24:00` in time validation so invalid values like `24:30` are rejected early. (#21410) thanks @adhitShet.
|
||||
|
||||
@@ -53,12 +53,12 @@ const MINIMAX_DEFAULT_VISION_MODEL_ID = "MiniMax-VL-01";
|
||||
const MINIMAX_DEFAULT_CONTEXT_WINDOW = 200000;
|
||||
const MINIMAX_DEFAULT_MAX_TOKENS = 8192;
|
||||
const MINIMAX_OAUTH_PLACEHOLDER = "minimax-oauth";
|
||||
// Pricing: MiniMax doesn't publish public rates. Override in models.json for accurate costs.
|
||||
// Pricing per 1M tokens (USD) — https://platform.minimaxi.com/document/Price
|
||||
const MINIMAX_API_COST = {
|
||||
input: 15,
|
||||
output: 60,
|
||||
cacheRead: 2,
|
||||
cacheWrite: 10,
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0.12,
|
||||
};
|
||||
|
||||
type ProviderModelConfig = NonNullable<ProviderConfig["models"]>[number];
|
||||
|
||||
@@ -42,12 +42,12 @@ export function resolveZaiBaseUrl(endpoint?: string): string {
|
||||
}
|
||||
}
|
||||
|
||||
// Pricing: MiniMax doesn't publish public rates. Override in models.json for accurate costs.
|
||||
// Pricing per 1M tokens (USD) — https://platform.minimaxi.com/document/Price
|
||||
export const MINIMAX_API_COST = {
|
||||
input: 15,
|
||||
output: 60,
|
||||
cacheRead: 2,
|
||||
cacheWrite: 10,
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0.12,
|
||||
};
|
||||
export const MINIMAX_HOSTED_COST = {
|
||||
input: 0,
|
||||
|
||||
Reference in New Issue
Block a user