The Orchestrator › Models › IBM Granite
IBM Granite: 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,...
Specifications
| Provider | IBM Granite |
| Model ID | ibm-granite/granite-4.2-8b |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2026-08-31 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | ibm-granite/granite-4.2-8b | $0.06 | $0.25 | 131K |
| standard | TrustedRouter | ibm-granite/granite-4.2-8b | $0.063 | $0.158 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.063 | $0.158 | 131K |
| 2026-11-14 | $0.06 | $0.25 | 131K |
Capabilities
Agentic tool useStructured outputsReasoning modeControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p