IBM: Granite 4.2 8B
Granite 4.2 8B is a reasoning model from IBM released on Aug 24, 2026. It reads text and writes text, with a 131K token context window and up to 118K tokens per reply.
Show moreShow less
It costs $0.10 per million input tokens and $0.15 per million output tokens. Cached input bills at $0.05, 50% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
4 providers serve it, including DevPass (LLM Gateway), Kilo Gateway and CoreWeave. The lowest input price is $0.06 per million tokens at DevPass (LLM Gateway).
- Modalities
- In / out price
- $0.10 / $0.15 per 1M
- Context
- 131K
- Max output
- 118K
- Released
- Aug 24, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Granite 4.2 8B pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.10 / 1M tokens | |
|---|---|---|
| Output | $0.15 / 1M tokens | |
| Cached input (read) | $0.05 / 1M tokens | 50% off input |
Granite 4.2 8B providers
4 providers serve it, including DevPass (LLM Gateway), Kilo Gateway and CoreWeave. The lowest input price is $0.06 per million tokens at DevPass (LLM Gateway). Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| DevPass (LLM Gateway) | $0.06 | $0.25 | $0.015 | 131K | 131K |
| Kilo Gateway | $0.06 | $0.25 | $0.015 | 131K | 118K |
| CoreWeave | $0.10 | $0.15 | $0.05 | 131K | 131K |
| NanoGPT | $0.10 | $0.15 | $0.05 | 131K | 118K |
What Granite 4.2 8B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Granite 4.2 8B through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to Granite 4.2 8B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 21 providers.
by qwenFeb 1, 2026$0.10/M input tokens$0.15/M output tokens21 providers
- 262K context
Reads text. Tool calling, reasoning. Served by 2 providers.
by inclusionaiSep 4, 2026$0.075/M input tokens$0.22/M output tokens2 providers
- 262K context
Reads text. Tool calling, reasoning. Served by 2 providers.
by inclusionaiAug 27, 2026$0.075/M input tokens$0.22/M output tokens2 providers
- 128K context
Reads text. Tool calling, structured output, reasoning. Served by 9 providers.
by openaiOct 29, 2025$0.07/M input tokens$0.20/M output tokens9 providers
- 131K context
Reads text. Tool calling, structured output, reasoning. Served by 3 providers.
by nvidiaAug 18, 2025$0.06/M input tokens$0.23/M output tokens3 providers
- 33K context
Reads text, images and audio. Tool calling, structured output, reasoning. Served by 2 providers.
by googleApr 2, 2026$0.10/M input tokens$0.10/M output tokens2 providers
More from IBM
- 131K context
Reads text.
by ibm-graniteOct 20, 2025$0.017/M input tokens$0.112/M output tokens
- 131K context
Reads text. Tool calling, structured output. Served by 2 providers.
by ibm-graniteOct 2, 2025$0.017/M input tokens$0.112/M output tokens2 providers
- 131K context
Reads text. Tool calling, structured output.
by ibm-graniteOct 2, 2025$0.0636/M input tokens$0.265/M output tokens
Granite 4.2 8B questions
How much does the Granite 4.2 8B API cost?
$0.10 per million input tokens and $0.15 per million output tokens, with cached input at $0.05. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Granite 4.2 8B?
131,072 tokens of input, and it can write up to 117,964 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Granite 4.2 8B?
4 providers serve it, including DevPass (LLM Gateway), Kilo Gateway and CoreWeave. The lowest input price is $0.06 per million tokens at DevPass (LLM Gateway). Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Granite 4.2 8B support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Granite 4.2 8B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Granite 4.2 8B released?
Aug 24, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Granite 4.2 8B?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting