Home › Providers › ibm-granite › IBM: Granite 4.2 8B

IBM: Granite 4.2 8B API Pricing

IBM: Granite 4.2 8B is an API model from ibm-granite. It costs $0.06 per 1M input tokens and $0.25 per 1M output tokens, with cached input at $0.015. Its context window is 131,072 tokens with up to 117,964 output tokens. A workload of 10M input + 2M output tokens costs about $1.1 per month.
Input
$0.06
per 1M tokens
Output
$0.25
per 1M tokens
Cached input
$0.015
per 1M tokens
Context window
131K
131,072 tokens
Blended (80/20)
$0.098
per 1M tokens

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

How much does IBM: Granite 4.2 8B cost for a real workload?

At 10M input + 2M output tokens per month, IBM: Granite 4.2 8B costs about $1.1 ($0.6 input + $0.5 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to IBM: Granite 4.2 8B?

Where to run IBM: Granite 4.2 8B

AI/ML API: one API key for 400+ models, including most models tracked here · Novita AI: pay-as-you-go APIs for open models (DeepSeek, Qwen, Llama and more) plus GPU cloud. Prices there follow each platform's own catalog and can differ from the list prices tracked here.

Run it on AI/ML API →Run it on Novita AI →

Disclosure: links to these platforms may be affiliate links — if you sign up or buy through them, LLMPrices may earn a commission at no extra cost to you.

Compare IBM: Granite 4.2 8B with other models

IBM: Granite 4.2 8B vs IBM: Granite 4.0 Micro

Frequently asked questions

How much does IBM: Granite 4.2 8B cost?

IBM: Granite 4.2 8B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens (list price, snapshot October 22, 2026). At 10M input + 2M output tokens per month that is about $1.1.

What is the context window of IBM: Granite 4.2 8B?

IBM: Granite 4.2 8B has a context window of 131,072 tokens and can return up to 117,964 output tokens per response.

What are cheaper alternatives to IBM: Granite 4.2 8B?

Cheaper models include Anthropic: Claude Haiku 5.5 (batch) ($0.05 in / $0.25 out), inclusionAI: Ling 3.1 Flash ($0.075 in / $0.225 out), OpenAI: GPT-6 Luna Pro (batch) ($0.05 in / $0.25 out). See the full list on this page.

Is IBM: Granite 4.2 8B free to use?

No. IBM: Granite 4.2 8B is a paid model at $0.06 input / $0.25 output per 1M tokens. 21 free models are listed on the free models page.

Provider: ibm-granite · Model ID: ibm-granite/granite-4.2-8b · Modality: text->text · Price snapshot October 22, 2026, refreshed daily. How we collect prices