All models
IBM
Granite 4.2 8B fastruns locally
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,...
Input / 1M
$0.060
USD per million tokens
Output / 1M
$0.25
USD per million tokens
Est. cost / token
$0.000000108
$0.11 per 1M, 3:1 mix
Context window
131K
max output 118K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 5.6 GB |
| Q3_K_M | fair | 6.2 GB |
| Q4_K_Mrecommended | good | 7.4 GB |
| Q5_K_M | very good | 8.3 GB |
| Q6_K | excellent | 9.3 GB |
| Q8_0 | near-lossless | 11.5 GB |
| F16 | lossless | 20.2 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.060 | $0.25 | $0.015 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.060
- Output
- $0.25
- Cached input
- $0.015
- Blended (3:1)
- $0.11
Details
- Company
- IBM
- Version
- 4.2
- Family
- Granite
- Released
- 2026-08-31
- Parameters
- 8.8B
- Max output
- 118K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 35 min ago