Skip to content
SF·SIX
SF·SIX / MODEL PROFILE

IBM Granite 4.2 8B

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,...

IBM Granite 4.2 8B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens at the standard tier, the lowest default-region price among the 2 providers SF·SIX tracks, from DeepInfra (bf16). Cached input reads cost $0.015 per 1M tokens. Updated ; prices checked .

Checked · Source: OpenRouter · Methodology

Developer
IBM Granite
Input modalities
text
Output modalities
text
Context tokens
131,072
Latest price observation
2026-10-17
Lowest paired standard token quote
$0.06 input / $0.25 output per 1M tokens

Dated price and provider records

Dated price and provider records
Provider and channelInputOutput or native rateUnit and statusSource and observation
DeepInfraOpenRouter$0.06$0.251M tokenspriced · USDOpenRouter2026-10-17
CoreWeaveOpenRouter$0.10$0.151M tokenspriced · USDOpenRouter2026-10-17

These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.

Compare AI API prices · Recent price changes · Estimate your monthly cost