IBM: Granite 4.2 8B pricing and limits

id ibm-granite/granite-4.2-8b · listed 2026-08-31

Input (per 1M tokens)	$0.060
Output (per 1M tokens)	$0.250
Cached input read (per 1M)	$0.015
Context window	131,072 tokens
Max output	117,964 tokens
Modalities	text → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.14.

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,...

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
DeepSeek: DeepSeek V4.1 Flash (batch)	$0.050	$0.150	1,048,576
Z.ai: GLM Flash Latest	$0.005	$0.199	1,048,576
Z.ai: GLM 5.3 Flash (batch)	$0.050	$0.180	1,048,576

Other ibm-granite models

IBM: Granite 4.0 Micro ($0.017 / $0.112)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=ibm-granite/granite-4.2-8b (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=ibm-granite. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with ibm-granite. Agent Exchange