@mate-academy/llm-gateway 8.8.4 → 8.10.0

package/README.md

@@ -2113,15 +2113,20 @@ describe('Custom LLM Integration Test', () => {
 The `LLMAPIModelNames` enum and `LLMAPI_AVAILABLE_MODELS` map drift as
 LLMAPI adds/renames models. The pipeline in
 [`scripts/sync-llmapi-models/`](scripts/sync-llmapi-models/README.md)
-reconciles them against `GET https://api.llmapi.ai/v1/models` under these
-rules:
+reconciles them against `GET https://api.llmapi.ai/v1/models` and the audio
+catalog at `GET https://api.llmapi.ai/audio-models` under these rules:
 
 - Unscoped aliases are always present; scoped aliases (`openai/…`, `azure/…`,
   `nebius/…`) only when LLMAPI advertises 2+ providers for that model.
-- Existing entries are never modified — the pipeline only appends new
-  entries and removes stale ones.
-- `maxOutputTokens` (the one field absent from the LLMAPI payload) is
-  researched from provider docs via web-search sub-agents.
+- Existing hand-tuned limits, capabilities, regular pricing, and configuration
+  are preserved. Cached input prices are refreshed from LLMAPI for every
+  existing and new route, including provider-specific overrides.
+- `maxOutputTokens` and any missing `maxInputTokens` are researched from
+  provider docs via web-search sub-agents.
+- TTS/STT limits and pricing, batch/streaming STT classification,
+  purpose-specific model maps, and default voice mappings are refreshed from
+  the audio catalog. Streaming-only STT models are exported separately and are
+  not exposed through the file-based `SpeechToText` service.
 
 See the linked README for the full classify → research → apply workflow.