Gemini 3.8 Flash-Lite TTS
gemini-3.8-flash-lite-ttsGemini 3.8 Flash-Lite TTS by Google: 8K context, 16K max output, with Audio, Streaming. Via WandAPI, Input (prompt) costs 1 Credits / M tokens, 70% below list price. Compatible with Gemini generateContent: swap the base URL and you are connected.
Capabilities
Listed exactly as the catalog flags them, including what this model does not support.
Audio
Audio input or speech output.
Streaming
Tokens arrive over SSE as they are generated; the first frame is forwarded immediately with no buffering. Claude Code, Codex and similar tools depend on this.
VisionNot supported
Natively multimodal: captioning, classification, visual Q&A, chart and screenshot understanding. Images are converted to tokens at the input rate.
Function CallingNot supported
Connect the model to external tools and APIs: it decides when to call which function and with what arguments, your code runs it. Force or forbid calls with tool_choice.
ReasoningNot supported
The model thinks before answering, which markedly improves multi-step planning and reasoning for coding, math and data analysis. Thinking tokens bill at the output rate.
Prompt CachingNot supported
Repeated prefixes (system prompts, long documents) hit the cache: reads cost far less than input, writes are priced by retention time.
Response SchemaNot supported
Constrain output to a JSON Schema you provide for predictable, type-safe results without parsing free text.
VideoNot supported
Video input understanding or video generation.
File InputNot supported
Upload PDFs and other documents directly; the model reads the whole document with native vision.
Web SearchNot supported
Vendor-hosted live web retrieval; the model decides when to search and cites sources.
RealtimeNot supported
Bidirectional low-latency voice / text sessions over WebSocket.
SessionNot supported
Server-side multi-turn context (e.g. previous_response_id in Responses) so you need not resend history.
MediaNot supported
Image / video / music generation endpoints.
Multipart FormNot supported
multipart/form-data file-upload requests.
Binary ResponseNot supported
Endpoints that return raw audio / image bytes.
Protocols & code samples
Change the base URL to WandAPI, keep everything else. Native protocols pass straight through; “adapted” ones are translated by the gateway.
Google GenAI SDK or any generateContent client: point the base URL at https://api.wandapi.com.
curl "https://api.wandapi.com/v1beta/models/gemini-3.8-flash-lite-tts:generateContent" \
-H "x-goog-api-key: $WANDAPI_KEY" \
-H "content-type: application/json" \
-d '{
"contents": [{"parts": [{"text": "Explain prompt caching in one sentence"}]}]
}'| Endpoint | Path | Mode |
|---|---|---|
| Token count | POST /v1beta/models/{model}:countTokens | native |
Full price list
List price → WandAPI price per channel, every pricing dimension, nothing hidden.
| Item | Unit | Google list price | Gemini官方分组 ×270% off |
|---|---|---|---|
| Input (prompt) | per 1M tokens | 1 Credits | |
| Audio output | per 1M tokens | 12 Credits |
“Off” is computed at 1 Credit = ¥1 and today’s rate: 1 − channel multiplier × (1 Credit in the list currency).
FAQ
How much does the Gemini 3.8 Flash-Lite TTS API cost?
Via WandAPI, Input (prompt) costs 1 Credits / M tokens, with 1 Credit = ¥1. That is 70% below the Google list price.
What are the context window and output limit of Gemini 3.8 Flash-Lite TTS?
Context window 8K tokens, up to 16K tokens per response.
Does Gemini 3.8 Flash-Lite TTS support function calling and structured outputs?
Function calling is not supported; structured outputs (JSON Schema) are not enabled.
One API key for Gemini 3.8 Flash-Lite TTS and 30+ models
Free credits on sign-up, pay as you go, no monthly fee.