LiteLLMModels

Speech 2.6 HD API Pricing

As of October 10, 2026, Speech 2.6 HD costs $100.00 per 1M characters on MiniMax.

Model ID minimax/speech-2.6-hdPrices updated Checked
Per 1M characters
$100.00
Providers
1
Added to LiteLLM
December 2025

Speech 2.6 HD 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
MiniMaxminimax/speech-2.6-hd$100.00–

What Speech 2.6 HD costs in practice

Narrating 500,000 characters

MiniMax$50.00

Use Speech 2.6 HD with LiteLLM

Call Speech 2.6 HD 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="minimax/speech-2.6-hd",
    input="Hello from LiteLLM",
    voice="alloy",
)
Proxy config.yaml
model_list:
  - model_name: speech-2.6-hd
    litellm_params:
      model: minimax/speech-2.6-hd
      # 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": "speech-2.6-hd",
    "input": "Hello from LiteLLM",
    "voice": "alloy"
  }'

Speech 2.6 HD FAQ

How much does Speech 2.6 HD cost?

Speech 2.6 HD costs $100.00 per 1M characters on MiniMax.

Which providers offer Speech 2.6 HD?

Speech 2.6 HD is available from MiniMax through LiteLLM, using the model name minimax/speech-2.6-hd.

How do I call Speech 2.6 HD with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="minimax/speech-2.6-hd", 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 Speech 2.6 HD?

Speech 2.6 HD 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.

LiteLLM docs: MiniMax.

Provider pages: MiniMax.