granite-4.2-30b · deepinfra
Granite-4.2-30B is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.
Input, $/1M $0.16
Output, $/1M $0.65
Context 131 072
Accepts —
Last checked 04.11.2026 12:00:14 UTC
Source —
Price alerts
API
This model type has no common request format: see the provider's documentation.
Source: AI Rate Card, https://airatecard.com/en/c/offer%3Adeepinfra%7Cibm-granite/granite-4.2-30b, prices checked 2026-11-04
Technical details
ID: offer:deepinfra|ibm-granite/granite-4.2-30b