LiteLLMModels

Granite 4.2 8B API Pricing

As of October 10, 2026, Granite 4.2 8B costs $0.10 per 1M input tokens and $0.15 per 1M output tokens on Weights & Biases, with cache reads at $0.05 per 1M tokens. It has a 131,000-token context window.

Model ID wandb/ibm-granite/granite-4.2-8bPrices updated Checked
Input
$0.10 / 1M tokens
Output
$0.15 / 1M tokens
Cache read
$0.05 / 1M tokens
Context window
131,000 tokens
Providers
1
Added to LiteLLM
September 10, 2026

Granite 4.2 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 LiteLLMInputOutputCache readContext
Weights & Biaseswandb/ibm-granite/granite-4.2-8b$0.10$0.15$0.05131K

What Granite 4.2 8B costs in practice

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

Weights & Biases$0.275

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

Weights & Biases$1.03

Granite 4.2 8B features

Use Granite 4.2 8B with LiteLLM

Call Granite 4.2 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-4.2-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: granite-4.2-8b
    litellm_params:
      model: wandb/ibm-granite/granite-4.2-8b
      # 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-4.2-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Granite 4.2 8B FAQ

How much does Granite 4.2 8B cost?

Granite 4.2 8B costs $0.10 per 1M input tokens and $0.15 per 1M output tokens on Weights & Biases, with cache reads at $0.05 per 1M tokens.

What is the context window of Granite 4.2 8B?

Granite 4.2 8B has a 131,000-token context window.

Which providers offer Granite 4.2 8B?

Granite 4.2 8B is available from Weights & Biases through LiteLLM, using the model name wandb/ibm-granite/granite-4.2-8b.

How do I call Granite 4.2 8B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="wandb/ibm-granite/granite-4.2-8b", 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 4.2 8B support?

Granite 4.2 8B supports reasoning and prompt caching.

When did LiteLLM add Granite 4.2 8B?

Granite 4.2 8B was added to LiteLLM's model price file on September 10, 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.