IBM › Granite 4.2 30B › Pricing
$0.16 / $0.65per 1M tokens in / out
$0.072per task at thinking?
Price sheetper 1M tokens
| Input | $0.16 | DeepInfra |
| Output | $0.65 | |
| Context | 128K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.16 | $0.65 | — |
In IBM's line-upper 1M in / out
| Granite 4.0 Micro | $0.017 / $0.11 | −86% |
| Granite 4.2 3B | $0.03 / $0.12 | −81% |
| Granite 4.0 H Small | $0.05 / $0.22 | −67% |
| Granite 4.2 8B | $0.06 / $0.25 | −62% |
| Granite 4.2 30B | $0.16 / $0.65 | this model |
Cheaper for the same workvs Granite 4.2 30B
| GPT-6 Luna max | -5% | score ×3 | $0.068 |
| MiMo v2.6 Flash thinkingOpen | -13% | score ×3 | $0.062 |
| Agnes 2.5 Pro Beta | -47% | score ×2.8 | $0.10 / $0.30 |
| Claude Haiku 5.5 medium | -34% | score ×2.7 | $0.047 |
| GPT-5.6 Luna high | -39% | score ×2.5 | $0.044 |
Pricing questions
How much does Granite 4.2 30B cost?›
$0.16 per 1M input tokens and $0.65 per 1M output tokens. One Intelligence Index task costs about $0.072 at the default effort.
Is Granite 4.2 30B free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
Is Granite 4.2 30B cheaper than Granite 4.1 30B?›
No: $0.16 / $0.65 against $0.10 / $0.25, 105% more per token.
What is a cheaper alternative to Granite 4.2 30B?›
GPT-6 Luna at max effort costs -5% per task with a score ×3 on Humanity's Last Exam.