@kreuzberg/liter-llm-node 1.4.0-rc.26 → 1.4.0-rc.27

package/index.d.ts

@@ -1,5 +1,5 @@
 // This file is auto-generated by alef — DO NOT EDIT.
-// alef:hash:d823102a0bf4208da86510efb01d1233dce33bf2bb3003d362fc4e11e76120e3
+// alef:hash:bceb888bcd835861a8bed9c7f699fb0085bc1c07e9e8a26778bc997f80b54b66
 // To regenerate: alef generate
 // To verify freshness: alef verify --exit-code
 // Issues & docs: https://github.com/kreuzberg-dev/alef
@@ -484,6 +484,21 @@ export interface JsPageDimensions {
 	height: number;
 }
 
+/**
+ * Breakdown of tokens used in the prompt portion of a request.
+ *
+ * `cached_tokens` is included in `Usage::prompt_tokens` — it is *not* an
+ * additional charge on top of the prompt token count. When pricing supports
+ * a `cache_read_input_token_cost`, the cached portion is billed at the
+ * discounted rate and the remainder at the regular input rate.
+ */
+export interface JsPromptTokensDetails {
+	/** Cached tokens present in the prompt. Defaults to 0 when absent. */
+	cachedTokens: number;
+	/** Audio input tokens present in the prompt. Defaults to 0 when absent. */
+	audioTokens: number;
+}
+
 /** Controls how much reasoning effort the model should use. */
 export declare enum JsReasoningEffort {
 	Low = "low",
@@ -671,6 +686,12 @@ export interface JsUsage {
 	completionTokens: number;
 	/** Total tokens used. Defaults to 0 when absent (some providers omit this). */
 	totalTokens: number;
+	/**
+	 * Breakdown of tokens used in the prompt, including cached tokens served
+	 * at the provider's discounted cache-read rate. Absent when the provider
+	 * does not return prompt-token details.
+	 */
+	promptTokensDetails: JsPromptTokensDetails;
 }
 
 export declare enum JsUserContent {

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@kreuzberg/liter-llm-node",
-	"version": "1.4.0-rc.26",
+	"version": "1.4.0-rc.27",
 	"description": "Native NAPI-RS bindings for liter-llm \u2014 high-performance LLM client powered by Rust",
 	"main": "index.js",
 	"types": "index.d.ts",