Skip to content
LLMs
IBM Granite logo

IBM: Granite 4.2 8B

by IBM Granite

IBM: Granite 4.2 8B is a large language model from IBM Granite. It costs $0.060 per million input tokens and $0.150 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.060
Output / 1M tokens
$0.150
Cached input / 1M
$0.015

On repeated prefixes

Context window
131K

tokens

Who serves it cheapest

2 hosts serve Granite 4.2 8B. Same weights, same API - the price difference is pure margin and routing.

Providers serving IBM: Granite 4.2 8B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
CoreWeaveCheapestbf16$0.060$0.150131K-100.0%
DeepInfrabf16$0.060$0.250131K-100.0%

The spread between CoreWeave and DeepInfra is 1.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
22.4
Agentic index
1.3

About 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,...

Specifications

IBM: Granite 4.2 8B specifications
Model IDibm-granite/granite-4.2-8b
ProviderIBM Granite
Context window131K tokens
Max output118K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - ibm-granite/granite-4.2-8b
ReleasedAugust 31, 2026

Cheaper alternatives

Models that cost less than Granite 4.2 8B while keeping at least half its context window and every input modality it supports.

Laguna XS 2.1

$0.060 in · $0.120 out

1.1× cheaper

Gemma 3 12B

$0.050 in · $0.150 out

1.1× cheaper

Mercury 2.5

$0.040 in · $0.150 out

1.2× cheaper

Command R7B (12-2024)

$0.037 in · $0.150 out

1.3× cheaper

Gemma 3 4B

$0.050 in · $0.100 out

1.3× cheaper

Frequently asked

How much does IBM: Granite 4.2 8B cost?

$0.060 per million input tokens and $0.150 per million output tokens. Cached input reads cost $0.015 per million tokens.

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

131K tokens, with up to 118K tokens of output per request.

Which provider serves IBM: Granite 4.2 8B cheapest?

CoreWeave at $0.060 per million input tokens - 1.3× cheaper than DeepInfra, the most expensive of the 2 hosts serving it.

Confirm against the source: IBM Granite official pricing.