# Granite 4.2 8B API prices

Granite 4.2 8B (granite) — 131k context, 131k max output.
6 metered per-token offers from 6 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.06 | $0.25 | $0.015 | 131k |
| DevPass (LLM Gateway) | $0.06 | $0.25 | $0.015 | 131k |
| LLM Gateway | $0.06 | $0.25 | $0.015 | 131k |
| OpenRouter | $0.06 | $0.25 | $0.015 | 131k |
| NanoGPT | $0.1 | $0.15 | $0.05 | 131k |
| CoreWeave | $0.1 | $0.15 | $0.05 | 131k |

## Summary

- Cheapest input: $0.06 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.15 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-08-31
- Inputs: text

## FAQ

### What is the cheapest Granite 4.2 8B API?

As of Oct 4, 2026, NanoGPT has the lowest Granite 4.2 8B output price at $0.15 per 1M tokens, and Kilo Gateway has the lowest input price at $0.06 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Granite 4.2 8B?

6 providers list Granite 4.2 8B on Sovyron; 6 of them sell it at a metered per-token price.

### Is Granite 4.2 8B free?

No provider in the Sovyron catalog lists a free tier for Granite 4.2 8B.

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

Granite 4.2 8B supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/granite-4-2-8b/
Full dataset: https://sovyron.com/data/catalog.json