---
title: "IBM Granite 4.2 8B API pricing: 2 providers compared"
description: "IBM Granite 4.2 8B API price per token from 2 providers: lowest listed USD 0.06 input and USD 0.15 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/granite-4.2-8b/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# IBM Granite 4.2 8B API pricing

Updated 2026-11-15

Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for IBM Granite 4.2 8B is CoreWeave Forge at USD 0.06 per 1M input tokens and USD 0.15 per 1M output tokens. The median across 2 standard prices is USD 0.06 / USD 0.20. Each price is read from the provider's own pricing page.

IBM · slug `granite-4.2-8b` · up to 131,072 tokens of context · 2 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/).

## Does IBM sell IBM Granite 4.2 8B directly?

IBM publishes no price for IBM Granite 4.2 8B on its own API that we could find, so this page compares hosts only.

## IBM Granite 4.2 8B model facts

Facts from IBM's model card for [`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

IBM Granite 4.2 8B: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes. The weights are in a public Hugging Face repository (ibm-granite/granite-4.2-8b) with no access gate. | [Hugging Face model API](https://huggingface.co/api/models/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “"private": false, "gated": false, 4 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | [IBM model card metadata](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “license: apache-2.0” |
| Total parameters | 8B | [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “Parameters \| 8B” |
| Context length | 128K natively (long-context extension to 512K) | [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “Context Length \| Natively Supports 128K (Long-context extension to 512K)” |
| Input and output | Text in, text out (the card's task tag is text-generation) | [IBM model card metadata](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “pipeline_tag: text-generation” |
| Tool calling | Yes | [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “Reasoning-Augmented Tool Calling: The model reasons about which tools to invoke and why” |
| Release date | 2026-08-25 | [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “Release Date \| August 25, 2026” |
| First published on Hugging Face (not necessarily the release date) | 2026-08-07 | [Hugging Face model API](https://huggingface.co/api/models/ibm-granite/granite-4.2-8b), checked 2026-11-16 · Quote: “"createdAt": "2026-08-07T16:29:09.000Z"” |

## IBM Granite 4.2 8B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 30% above the cheapest.

IBM Granite 4.2 8B API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[CoreWeave Forge](https://broadrouter.com/llm-api-pricing/providers/coreweave/)** cheapest · `ibm-granite/granite-4.2-8b` · Quote: “IBM Granite 4.2 8B $0.06 $0.15 $0.015” | USD 0.06 | USD 0.015 | USD 0.15 | USD 0.0825 | 131,072 | not stated | [CoreWeave Forge page](https://coreweave.com/forge-pricing/inference-agents) · checked 2026-11-15 · re-checked 2026-11-16 |
| 2 | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** · `ibm-granite/granite-4.2-8b` · Quote: “$0.06 in $0.25 out $0.015 cached / 1M tokens” | USD 0.06 | USD 0.015 | USD 0.25 | USD 0.1075 | 131,072 | not stated | [DeepInfra page](https://deepinfra.com/ibm-granite/granite-4.2-8b) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20IBM%20Granite%204.2%208B%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fgranite-4.2-8b%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does IBM Granite 4.2 8B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=granite-4.2-8b). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on IBM Granite 4.2 8B, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **CoreWeave Forge** | USD 5.67 | USD 13.41 | USD 52.65 |
| **DeepInfra** | USD 7.47 | USD 14.91 | USD 61.65 |

For the support chatbot, the cheapest price (CoreWeave Forge, USD 5.67 a month) saves USD 0.9 against the median (USD 6.57). For the coding agent the gap is USD 4.50 a month (8% lower).

## Which IBM Granite 4.2 8B provider is cheapest for your traffic?

CoreWeave Forge has the lowest input price (USD 0.06) and the lowest output price (USD 0.15), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

IBM Granite 4.2 8B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **CoreWeave Forge** | USD 0.0825 cheapest | USD 0.06562 cheapest | USD 0.05212 cheapest |
| **DeepInfra** | USD 0.1075 | USD 0.09062 | USD 0.07712 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

Both providers publish a cached-input price below the input price: CoreWeave Forge (75% off), DeepInfra (75% off).

Both providers offer 131,072 tokens of context.

## Estimate your own bill

-   [LLM API cost calculator with IBM Granite 4.2 8B preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=granite-4.2-8b): your traffic and cache rate, against any of 431 models.
-   [Token counter](https://broadrouter.com/tools/token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

Priced closest from other makers: [NVIDIA Nemotron 3.5 Lightning 30B A3B](https://broadrouter.com/llm-api-pricing/nemotron-3.5-lightning/) (NVIDIA, USD 0.085) · [DeepSeek V4 Flash](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash/) (DeepSeek, USD 0.0875) · [NVIDIA Nemotron 3 Nano 30B A3B](https://broadrouter.com/llm-api-pricing/nemotron-3-nano-30b-a3b/) (NVIDIA, USD 0.0875).

[All 431 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the IBM Granite 4.2 8B API cost per token?

From USD 0.06 per 1M input tokens (USD 0.00000006 per token) and USD 0.15 per 1M output tokens (USD 0.00000015 per token) at the lowest standard prices we found. The median of 2 standard prices is USD 0.06 input and USD 0.20 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for IBM Granite 4.2 8B?

Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is CoreWeave Forge, ranked on a blend of 3 input tokens to 1 output token (USD 0.0825 per 1M). For input alone the lowest price is USD 0.06 (CoreWeave Forge and 1 other, tied); for output alone, USD 0.15 (CoreWeave Forge). Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does IBM sell IBM Granite 4.2 8B on its own API?

IBM publishes no price for IBM Granite 4.2 8B on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is CoreWeave Forge at USD 0.06 / USD 0.15 per 1M tokens.

### Does IBM Granite 4.2 8B have cached input pricing?

All 2 standard prices include one. The lowest is USD 0.015 per 1M at CoreWeave Forge; the median is USD 0.015. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

### What is the IBM Granite 4.2 8B context window?

131,072 tokens on every provider that states it.

### How much does a coding agent cost per month on IBM Granite 4.2 8B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 52.65 a month at CoreWeave Forge, USD 57.15 at the median price and USD 61.65 at DeepInfra. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=granite-4.2-8b).

### Is IBM Granite 4.2 8B free to use through an API?

No provider in our data lists a free price for IBM Granite 4.2 8B as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is IBM Granite 4.2 8B open source, with open weights, and what is its licence?

IBM publishes the weights on Hugging Face as [`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b), in a public repository with no access gate. The licence, as the [IBM model card metadata](https://huggingface.co/ibm-granite/granite-4.2-8b) states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from IBM's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does IBM Granite 4.2 8B have?

Total parameters, as the [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b) states them: 8B. (checked 2026-11-16; BroadNet did not verify these figures.)

### Does IBM Granite 4.2 8B support tool calling?

Yes, according to the [IBM model card](https://huggingface.co/ibm-granite/granite-4.2-8b): “Reasoning-Augmented Tool Calling: The model reasons about which tools to invoke and why” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.

### How do I call IBM Granite 4.2 8B with the OpenAI SDK?

BroadNet does not serve IBM Granite 4.2 8B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with `OpenAI(base_url=..., api_key=...)` and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: [DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/) (`https://api.deepinfra.com/v1/openai`, model `ibm-granite/granite-4.2-8b`). Each provider page quotes the provider's docs with a check date.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-granite-4.2-8b&utm_content=page-cta) ·

**Sources**

-   [CoreWeave Forge: pricing (checked 2026-11-15)](https://coreweave.com/forge-pricing/inference-agents)
-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/ibm-granite/granite-4.2-8b)
