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.
At a glance
- Input / 1M
- $0.06
- Output / 1M
- $0.25
- Context
- 131K
- Max output
- 118K
- Intelligence
- 11.1
- Released
- Aug 2026
Pricing
Granite 4.2 8B API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.06 |
|---|---|
| Output tokensPer 1M tokens | $0.25 |
| Cached input (read)Per 1M tokens | $0.02 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.25
per 1,000 requests
Coding task
30K in, 4K out
$2.80
per 1,000 requests
Long document summary
150K in, 2K out
$9.50
per 1,000 requests
Benchmarks
Granite 4.2 8B benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
11.1
Coding index
22.4
Agentic index
1.3
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 131K tokens
- Max output
- 118K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- High, Low, None
- Release date
- August 31, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Granite 4.2 8B vs other models
See how Granite 4.2 8B stacks up head to head on price, benchmarks, and features.
VS
Granite 4.2 8B vs Gemini 2.5 Flash Lite
IBM vs Google
See comparisonVS
Granite 4.2 8B vs gpt-oss-120b
IBM vs OpenAI
See comparisonVSGranite 4.2 8B vs Gemma 4 31B
IBM vs Google
See comparisonVSGranite 4.2 8B vs gpt-oss-20b
IBM vs OpenAI
See comparisonVSGranite 4.2 8B vs GPT-5 Nano
IBM vs OpenAI
See comparisonVS
Granite 4.2 8B vs Qwen3 235B A22B Instruct 2507
IBM vs Qwen
See comparisonAlternatives
Granite 4.2 8B alternatives
Similar models worth considering, and where each one has the edge.
Gemma 4 31B
OpenAI
GPT-5 Nano
Inception
Mercury 2.5
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Granite 4.2 8B cost?
Granite 4.2 8B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens through the API. A typical chat message costs about $0.25 per 1,000 messages.
What is the context window of Granite 4.2 8B?
Granite 4.2 8B accepts up to 131K tokens of input and can write up to 118K tokens in a single response.
What is the best alternative to Granite 4.2 8B?
Gemma 4 31B from Google is a strong alternative. It offers: higher intelligence score, larger 262k context, accepts image and video.
Can I use Granite 4.2 8B alongside other models?
Yes. Shortcut Chat sends one prompt to Granite 4.2 8B and any other models you pick at the same time, so you can compare answers side by side.
Try Granite 4.2 8B next to every other model.
Use Granite 4.2 8B alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.