impulse

Gemini 3.1 Flash TTS

Frontier labSpeech
API id gemini-3.1-flash-tts
Input / 1M
$2.00
at Replicate
Output / 1M
$40.00
at Replicate
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Replicate, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$2.00$40.00

What it costs a month

At Replicate list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$3,600
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$2,400
  • Coding agent1,000 requests a day, 40K in / 2K out$4,800
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$14,400
Use your own numbers

Where to run it

1 host serve Gemini 3.1 Flash TTS. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
gemini-3.1-flash-tts
$2.00 / $40.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Audio

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Replicate.

Smaller Google models

Other frontier labs

  • GPT-4o Mini TTS
    OpenAI · on OpenAI
    $0.60 / $10.00
    Has every key capability
    74% less

Open-weight picks

Model line

Newer and older versions, at each lab's own price.

  1. UndatedGemini 3.8 Flash TTSLatest$0.50 / $9.00
  2. UndatedGemini 3.1 Flash TTSThis page$2.00 / $40.00
  3. UndatedGemini 2.5 Flash TTS$0.50 / $10.00

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/gemini-3.1-flash-tts",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Gemini 3.1 Flash TTS cost?

On Replicate, Gemini 3.1 Flash TTS costs $2.00 per million input tokens and $40.00 per million output tokens.

Which APIs offer Gemini 3.1 Flash TTS?

Gemini 3.1 Flash TTS runs on 1 API: Replicate.

Is Gemini 3.1 Flash TTS being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Gemini 3.1 Flash TTS?

Yes. Gemini 3.8 Flash TTS is the newest model in this line.

What are cheaper alternatives to Gemini 3.1 Flash TTS?

Models that cost less and keep most of what it can do: Gemini 2.5 Pro TTS on Vertex AI (50% less), GPT-4o Mini TTS on OpenAI (74% less) and Qwen Audio 3.1 TTS Flash on Alibaba DashScope (94% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemini 3.1 Flash TTS's API model id?

Use gemini-3.1-flash-tts with Replicate.

Sources

Raw catalog entry for gemini-3.1-flash-tts on Replicate
{
  "input_cost_per_token": 0.000002,
  "litellm_provider": "replicate",
  "mode": "audio_speech",
  "output_cost_per_token": 0.00004,
  "source": "https://replicate.com/google/gemini-3.1-flash-tts"
}