LiteLLMModels

Granite 4.1 8B API Pricing

As of October 10, 2026, Granite 4.1 8B costs $0.05 per 1M input tokens and $0.10 per 1M output tokens on Weights & Biases. It has a 131,000-token context window.

Model ID wandb/ibm-granite/granite-4.1-8bPrices updated Checked
Deprecated: Weights & Biases lists October 5, 2026 as the deprecation date for wandb/ibm-granite/granite-4.1-8b.
Input
$0.05 / 1M tokens
Output
$0.10 / 1M tokens
Context window
131,000 tokens
Providers
1
Added to LiteLLM
August 27, 2026

Granite 4.1 8B 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 LiteLLMInputOutputContext
Weights & Biaseswandb/ibm-granite/granite-4.1-8b$0.05$0.10131K

What Granite 4.1 8B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Weights & Biases$0.15

100 long-document requests with 100,000 input and 2,000 output tokens each

Weights & Biases$0.52

Granite 4.1 8B features

Use Granite 4.1 8B with LiteLLM

Call Granite 4.1 8B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="wandb/ibm-granite/granite-4.1-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: granite-4.1-8b
    litellm_params:
      model: wandb/ibm-granite/granite-4.1-8b
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "granite-4.1-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Granite 4.1 8B FAQ

How much does Granite 4.1 8B cost?

Granite 4.1 8B costs $0.05 per 1M input tokens and $0.10 per 1M output tokens on Weights & Biases.

What is the context window of Granite 4.1 8B?

Granite 4.1 8B has a 131,000-token context window.

Which providers offer Granite 4.1 8B?

Granite 4.1 8B is available from Weights & Biases through LiteLLM, using the model name wandb/ibm-granite/granite-4.1-8b.

How do I call Granite 4.1 8B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="wandb/ibm-granite/granite-4.1-8b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Granite 4.1 8B support?

It does not support image input.

When did LiteLLM add Granite 4.1 8B?

Granite 4.1 8B was added to LiteLLM's model price file on August 27, 2026.

Is Granite 4.1 8B being deprecated?

Weights & Biases deprecated wandb/ibm-granite/granite-4.1-8b on October 5, 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. Provider pricing pages:

LiteLLM docs: Weights & Biases.

Provider pages: Weights & Biases.