Skip to content

IBM: Granite 4.2 8B

IBM

IBM: Granite 4.2 8B by IBM costs $0.06 per 1M input tokens and $0.25 per 1M output tokens, with a 131K-token context window.

Pricing

Input (per 1M tokens)
$0.06
Output (per 1M tokens)
$0.25
Cached input (per 1M)
$0.02

Specifications

Provider
IBM
Context window
131K tokens
Parameters
—
Released
—
Open weights
—
Frontier model
No
Hugging Face
ibm-granite/granite-4.2-8b

Benchmarks

Speed & latency

Time to first token
0.20s
Output speed
150 tok/s

Fastest host: deepinfra (via hf-router).

Compare IBM: Granite 4.2 8B with…

FAQ

How much does IBM: Granite 4.2 8B cost?

IBM: Granite 4.2 8B is priced at $0.06 per 1M input tokens and $0.25 per 1M output tokens. Output tokens cost more than input.

What is IBM: Granite 4.2 8B's context window?

IBM: Granite 4.2 8B supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.

Is IBM: Granite 4.2 8B open weight?

Open-weight status for IBM: Granite 4.2 8B is not recorded in our dataset.

Data as of 2026-10-14. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.