Back to all models

Granite 4.2 8B

IBM's dense 8B reasoning model for math, code generation, multilingual dialogue, and agentic workflows.

granite-4.2-8b
STABLEGet StartedView uptime
131,072 context
Released September 1, 2026
Starting at $0.06/M input tokens
Starting at $0.25/M output tokens
Streaming
Tools
Reasoning
JSON Output
No ratings yetSign in to rate

Select Provider

All Providers for Granite 4.2 8B

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 131.1kQuant: bf16
Input
$0.06
/M tokens
Cache Read
$0.015
/M tokens
Output
$0.25
/M tokens
Get Started

Frequently asked questions

What is Granite 4.2 8B?

IBM's dense 8B reasoning model for math, code generation, multilingual dialogue, and agentic workflows. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Granite 4.2 8B cost?

Pricing for Granite 4.2 8B on LLM Gateway starts at $0.06 per million input tokens and $0.25 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Granite 4.2 8B?

Granite 4.2 8B supports a context window of up to 131,072 tokens on its largest provider deployment.

Which providers serve Granite 4.2 8B?

Granite 4.2 8B is served by DeepInfra through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Granite 4.2 8B support tool calling and structured outputs?

Granite 4.2 8B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).

When was Granite 4.2 8B released?

Granite 4.2 8B was released on September 1, 2026.