@mate-academy/llm-gateway 7.5.1 → 7.6.1

package/README.md

@@ -547,6 +547,32 @@ if (result.data) {
 }
 ```
 
+#### Token Usage and Cost
+
+Successful completion and transcription results expose two optional fields: `usage`
+(`LLMModelUsage`) with the provider-reported token counts, and `cost`
+(`LLMCostsResult`) with the absolute USD cost for the call, derived from that usage
+and the model's pricing. Both are present only on the success branch (absent when
+`result.error` is set), so read them after narrowing:
+
+```typescript
+const result = await completionService.sendMessage({
+  message: { /* ... */ },
+  model: preferredModel,
+  schema: mySchema,
+});
+
+if (!('error' in result) && result.usage) {
+  console.log('Input tokens:', result.usage.inputTextTokens);
+  console.log('Output tokens:', result.usage.outputTextTokens);
+  console.log('Total cost (USD):', result.cost?.total);
+}
+```
+
+For the LLMAPI provider, the structured-output result's `usage` (and the `cost`
+derived from it) includes the JSON-fix call's tokens (summed into the primary
+call's usage) when a fix was required.
+
 #### Provider Support
 
 - **OpenAI**: Uses native `response_format` with `json_schema` for optimal performance