Identity
- Status
- active
- Developer ID
ibm-granite/granite-4.2-8b- Released
- Aug 25, 2026
- Version
- Granite 4.2 8B
- License
- apache-2.0
IBMGranite 4.2 8B
Granite 4.2 8B is IBM's mid-size open-weight dense reasoning model with native 128K context, optional 512K long-context extension, flexible thinking modes, and tool calling.
- Context
- 131,072 tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Aug 25, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.060 | $0.25 | $0.015 | — | Sep 3, 2026 | Provider-reported |
 OpenrouterAvailable | $0.10 | $0.15 | $0.050 | — | Sep 3, 2026 | Provider-reported |
Benchmarks
All benchmark results →| LMArena Text Arenatext-2026-09-01-011508720696 | 1,317.93 | — | 3,119 | granite-4.2-8b; 95% CI [1306.62269586, 1329.24728966]; votes 3119; rank 219unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Context
- 131,072 tokens
- Maximum output
- Unknown
- Total parameters
- 8,791,592,960
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, structured outputs, tools
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesgranite-4.2-8b, Granite 4.2 8B, ibm-granite/granite-4.2-8b, ibm-granite/granite-4.2-8b-fp8, ibm-granite/granite-4.2-8b-GGUF, ibm-granite/granite-4.2-8b-mxfp4, ibm-granite/granite-4.2-8b-nvfp4
Explicit Unknowns
- Maximum output
- Tokenizer
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
ibm-granite/granite-4.2-8b developer model repositoryIBM · observed Sep 2, 2026DeepInfra OpenAI-compatible model catalogDeepInfra · observed Sep 2, 2026ibm-granite/granite-4.2-8b config.json at 7fce579a7fbbIBM · observed Sep 2, 2026ibm-granite/granite-4.2-8b README.md at 7fce579a7fbbIBM · observed Sep 2, 2026ibm-granite/granite-4.2-8b immutable Hub API metadataIBM · observed Sep 2, 2026Introducing Granite 4.2IBM · observed Sep 2, 2026Hugging Face Publishers catalogHugging Face Publishers · observed Sep 2, 2026OpenRouter model catalog APIOpenRouter · observed Aug 28, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs |  Gemma 4 12BGoogle DeepMind | cross-developer peerstext | |
| vs | family variantstext | ||
| vs | Gemma 4 E2BGoogle DeepMind | cross-developer peerstext | |
| vs |  gpt-oss-20bOpenai | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs |  Phi-4-mini-reasoningMicrosoft | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs |  Command A TranslateCohere | cross-developer peerstext | |
| vs |  Llama-3.1-8BMeta | cross-developer peerstext |
Questions
Granite 4.2 8B FAQs
What is Granite 4.2 8B?+
Granite 4.2 8B is IBM's mid-size open-weight dense reasoning model with native 128K context, optional 512K long-context extension, flexible thinking modes, and tool calling. It is developed by IBM and its current sourced lifecycle status is active.
What inputs and outputs does Granite 4.2 8B support?+
Granite 4.2 8B's current record lists Text as input and Text as output.
How much context does Granite 4.2 8B support?+
The current record lists a 131,072-token context window and does not report a maximum output length.
Is Granite 4.2 8B available through an API?+
Granite 4.2 8B is marked as API-available. The directly sourced provider records currently include Deepinfra, Hugging Face, and Openrouter.
How large is Granite 4.2 8B?+
The current record lists 8,791,592,960 total parameters and an unknown active parameter count. Its architecture is GraniteForCausalLM.
What capabilities and tasks does Granite 4.2 8B support?+
Granite 4.2 8B's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are code, reasoning, and text.
How much does Granite 4.2 8B cost through an API?+
The lowest directly sourced prices currently attached to Granite 4.2 8B are $0.060 per million input tokens through Deepinfra and $0.15 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Granite 4.2 8B be self-hosted?+
Granite 4.2 8B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Granite 4.2 8B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are granite-4.2-8b, Granite 4.2 8B, ibm-granite/granite-4.2-8b, ibm-granite/granite-4.2-8b-fp8, ibm-granite/granite-4.2-8b-GGUF, ibm-granite/granite-4.2-8b-mxfp4, and ibm-granite/granite-4.2-8b-nvfp4.
Which models can Granite 4.2 8B be compared with?+
The current compatible peer set includes Granite 4.2 3B, Granite 4.2 30B, granite-4.1-8b, Gemma 4 12B, and granite-4.1-3b. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →