Granite 4.2 8B
Granite 4.2 8B is a general-purpose chat-tuned model. Available via IBM. 131,072-token context. Budget pricing.
Granite 4.2 8B is a efficient AI model from IBM. It costs $0.0600 per million input tokens and $0.2500 per million output tokens (blended $0.1170/M), with a 131,072-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
0.0%over 10 days · hover to read
From OpenRouter's listing, read on 17 Nov 2026.
- Solid general chat performance
- Reasonable instruction following
- General chat
- Drafting and rewriting
- Personal productivity
Benchmarks
More from IBM
See all 5 →Price history
2 recorded changes| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 8 Nov 2026 | Output | $0.1500 | $0.2500 | +67% |
| 8 Nov 2026 | Input | $0.1000 | $0.0600 | -40% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does Granite 4.2 8B cost?
Granite 4.2 8B costs $0.0600 per million input tokens and $0.2500 per million output tokens, for a blended reference rate of $0.1170 per million tokens.
What is Granite 4.2 8B's context window?
Granite 4.2 8B supports up to 131,072 tokens of context in a single request.
What is Granite 4.2 8B best for?
Granite 4.2 8B is well suited to Solid general chat performance, Reasonable instruction following and General chat.
Who makes Granite 4.2 8B?
Granite 4.2 8B is developed and served by IBM.
