Granite 4.2 30B
Granite 4.2 30BRankingin thinking mode?
Alternatives?
CheaperMiMo v2.6 FlashunstatedOpenwins 63%-38%$0.14 / $0.28Memory (4-bit): 18 GB → 186 GB+4
BetterClaude Haiku 5.5highwins 54%-29%$0.079Remove sampling parameters+5
OpenGemma 4 31Bunstatedwins 60%-43%$0.10 / $0.34Memory (4-bit): 18 GB → 19 GB
CheaperGLM 5.3 FlashunstatedOpenwins 63%-16%$0.15 / $0.50Memory (4-bit): 18 GB → 193 GB+5
CheaperHy3unstatedOpenwins 59%-18%$0.13 / $0.53Memory (4-bit): 18 GB → 179 GBMiMo v2.6 FlashunstatedOpenwins 63%-38%$0.14 / $0.28Memory (4-bit): 18 GB → 186 GB+4GLM 5.3 FlashunstatedOpenwins 63%-16%$0.15 / $0.50Memory (4-bit): 18 GB → 193 GB+5Gemma 4 31BunstatedOpenwins 60%-43%$0.10 / $0.34Memory (4-bit): 18 GB → 19 GBHy3unstatedOpenwins 59%-18%$0.13 / $0.53Memory (4-bit): 18 GB → 179 GBMiMo v2.5unstatedOpenwins 59%-38%$0.14 / $0.28Memory (4-bit): 18 GB → 186 GBClaude Haiku 5.5highwins 54%-29%$0.079Remove sampling parameters+5
GPT-5.6 Lunaxhighwins 58%+59%$0.085GPT-5.6 Terraxhighwins 59%+1,493%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 60%+1,316%$0.72Remove unsupported parameters+5GPT-5.6 Solxhighwins 61%+2,732%$1.18Gemma 4 31BunstatedOpenwins 60%-43%$0.10 / $0.34Memory (4-bit): 18 GB → 19 GB
Qwen3.8 27BunstatedOpenwins 59%+238%$0.42 / $2.55max_tokens range · QwenCloud+4Gemma 4 26B A4BunstatedOpenwins 59%-7%$0.15 / $0.60Qwen 3.5 27BunstatedOpenwins 56%+192%$0.30 / $2.40Qwen 3.5 35B A3BunstatedOpenwins 54%+143%$0.25 / $2Memory (4-bit): 18 GB → 22 GBGranite 4.2 8BunstatedOpenwins 44%—$0.06 / $0.25Granite 4.2 3BunstatedOpenwins 41%—$0.03 / $0.12Granite 4.1 8BunstatedOpenwins 40%——Granite 4.0 H SmallunstatedOpenwins 34%—$0.05 / $0.22Memory (4-bit): 18 GB → 19 GBGranite 4.1 30BOpenn/a—$0.10 / $0.25Granite 4.1 3BOpenn/a——Granite 4.0 350Mnon-thinkingOpenn/a——Context: 128K → 33KGranite 4.0 H 350MOpenn/a——Context: 128K → 33KAll IBM models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Granite 4.2 30B cost?›
$0.16 per 1M input tokens and $0.65 per 1M output tokens (cheapest host: DeepInfra). A typical benchmark task costs about $0.072 at default effort.
Is Granite 4.2 30B free to use?›
There is no free API; the cheapest paid price is $0.16 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Granite 4.2 30B, and what is it best at?›
#171 of 336 in Chat & Knowledge, #77 of 134 in Coding, #105 of 135 in Agents & Tool Use, #133 of 197 in Writing & Language, #109 of 135 in Vision & Documents.
Is Granite 4.2 30B better than Nova 2 Lite?›
On Arena Text · English, Granite 4.2 30B scores 1,382.2 vs 1,384.6 — about the same.
How can I use Granite 4.2 30B?›
Through the API of DeepInfra.
What is the context window of Granite 4.2 30B?›
128K tokens.
When was Granite 4.2 30B released? Is there a newer version?›
Released 2026-08-25. It is the current version in its line.
Is Granite 4.2 30B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Granite 4.2 30B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Granite 4.2 30B read images?›
No, it accepts text only.
What is Granite 4.2 30B?›
Granite 4.2 30B is an open-weights language model from IBM, released Aug 2026, the successor to Granite 4.1 30B.
What are the best alternatives to Granite 4.2 30B?›
MiMo v2.6 Flash (cheaper), Claude Haiku 5.5 (better), Gemma 4 31B (open weights).