Granite Speech 4.1 2B API Pricing
replicate/ibm-granite/granite-speech-4.1-2b- Price
- $0.03 per 1M tokens
As of November 21, 2026, Granite Speech 4.1 2B costs $0.03 per 1M tokens on Replicate.
Granite Speech 4.1 2B 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.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Replicate | replicate/ibm-granite/granite-speech-4.1-2b | $0.03 | $0.25 | – |
Use Granite Speech 4.1 2B with LiteLLM
Call Granite Speech 4.1 2B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/audio/transcriptions. LiteLLM tracks the cost of every request at these prices.
from litellm import transcription
response = transcription(
model="replicate/ibm-granite/granite-speech-4.1-2b",
file=open("audio.mp3", "rb"),
)model_list:
- model_name: granite-speech-4.1-2b
litellm_params:
model: replicate/ibm-granite/granite-speech-4.1-2b
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/audio/transcriptions \ -H "Authorization: Bearer $LITELLM_API_KEY" \ -F model="granite-speech-4.1-2b" \ -F file=@audio.mp3
Granite Speech 4.1 2B FAQ
How much does Granite Speech 4.1 2B cost?
Granite Speech 4.1 2B costs $0.03 per 1M tokens on Replicate.
Which providers offer Granite Speech 4.1 2B?
Granite Speech 4.1 2B is available from Replicate through LiteLLM, using the model name replicate/ibm-granite/granite-speech-4.1-2b.
How do I call Granite Speech 4.1 2B with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="replicate/ibm-granite/granite-speech-4.1-2b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/audio/transcriptions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Granite Speech 4.1 2B?
Granite Speech 4.1 2B was added to LiteLLM's model price file on November 11, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Replicate.
Provider pages: Replicate.