LiteLLMModels

Generative API Pricing

As of October 10, 2026, Generative costs $30.00 per 1M characters on AWS - Polly.

Model ID aws_polly/generativePrices updated Checked
Per 1M characters
$30.00
Providers
1
Added to LiteLLM
December 2025

Generative pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMPer 1M charsContext
AWS - Pollyaws_polly/generative$30.00–

What Generative costs in practice

Narrating 500,000 characters

AWS - Polly$15.00

Use Generative with LiteLLM

Call Generative through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/audio/speech. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import speech

response = speech(
    model="aws_polly/generative",
    input="Hello from LiteLLM",
    voice="alloy",
)
Proxy config.yaml
model_list:
  - model_name: generative
    litellm_params:
      model: aws_polly/generative
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "generative",
    "input": "Hello from LiteLLM",
    "voice": "alloy"
  }'

Generative FAQ

How much does Generative cost?

Generative costs $30.00 per 1M characters on AWS - Polly.

Which providers offer Generative?

Generative is available from AWS - Polly through LiteLLM, using the model name aws_polly/generative.

How do I call Generative with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="aws_polly/generative", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/audio/speech from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Generative?

Generative was added to LiteLLM's model price file in December 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: AWS - Polly.

Provider pages: AWS - Polly.