Google · Voice & Music

Gemini 2.5 Pro Preview TTS

Catalog data · checked Nov 16, 2026

Gemini 2.5 Pro Preview TTS is a multimodal model from Google, released in May 2025. It reads text and writes audio, with a context window of 8.2K tokens and up to 16.4K output tokens per answer. It costs $1 per million input tokens and $20 per million output tokens.

Calculate my costCompare

Input price$1per 1M tokens
Output price$20per 1M tokens
Context window8.2Ktokens per request
Max output16.4Ktokens per answer
ReleasedMay 2025May 2025
Knowledge cutoffJan 2025training data ends
WeightsClosedAPI only

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$5.8
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens outtoo long
10,000 product descriptions300 input and 200 output tokens per text$43
One day of agentic codingabout 3M input and 150K output tokens across many calls$6

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Questions & answers

How much does Gemini 2.5 Pro Preview TTS cost?

Gemini 2.5 Pro Preview TTS costs $1 per 1 million input tokens and $20 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Gemini 2.5 Pro Preview TTS?

Gemini 2.5 Pro Preview TTS can process up to 8,192 tokens per request and return up to 16,384 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Gemini 2.5 Pro Preview TTS support tool calling?

No tool calling is listed for this model in the catalog.