Granite 4.1 30B
Granite 4.1 30BRanking?
Alternatives?
CheaperSolar Mini 4×3.5-36%$0.37
BetterGPT-6 Lunalow×3.1+45%$0.005Function calling only with none · Chat Completions+3
OpenMuse Glimmer 30Bhigh×3.5+264%$0.058Memory (4-bit): 17 GB → 18 GB
CheaperLing 3.0 Flash VLthinkingOpen×3.3-35%$0.06 / $0.18Memory (4-bit): 17 GB → 75 GBCheaperLing 3.0 Flash FinthinkingOpen×3.1-35%$0.06 / $0.18Memory (4-bit): 17 GB → 76 GBSolar Mini 4×3.5-36%$0.37Ling 3.0 Flash VLthinkingOpen×3.3-35%$0.06 / $0.18Memory (4-bit): 17 GB → 75 GBLing 3.0 Flash FinthinkingOpen×3.1-35%$0.06 / $0.18Memory (4-bit): 17 GB → 76 GBLing 3.0 FlashthinkingOpen×3.1-35%$0.06 / $0.18Memory (4-bit): 17 GB → 76 GB
Qwen 3.5 9BthinkingOpen×3-33%$0.21GPT-6 Lunalow×3.1+45%$0.005Function calling only with none · Chat Completions+3
Gemma 4 E4BthinkingOpen+35%-71%$0.008Context: 131K → 128KGPT-5.6 Lunalow×3+227%$0.01
Ministral 3 8B 2512Open+8%+9%$0.011GPT OSS 20BhighOpen+46%-74%$0.011Muse Glimmer 30BhighOpen×3.5+264%$0.058Memory (4-bit): 17 GB → 18 GBQwen3.8 27BxhighOpen×3.5+595%$1.01max_tokens range · QwenCloud+4Qwen 3.5 27BthinkingOpen×3.3+500%$0.30 / $2.40Qwen3.6 27BthinkingOpen×3.3+882%$0.62Qwen 3.5 35B A3BthinkingOpen×3+400%$0.25 / $2Memory (4-bit): 17 GB → 22 GBGranite 4.2 30BthinkingOpen×2.1—$0.072Context: 131K → 128K+1Granite 4.2 8BthinkingOpen+90%—$0.024Context: 131K → 128KGranite 4.2 3BthinkingOpensame—$0.006Context: 131K → 128KGranite 4.1 8Bnon-thinkingOpen-44%——Granite 4.0 H Smallnon-thinkingOpen-52%—$0.05 / $0.22Context: 131K → 128K+1Granite 4.0 H 1BOpen-70%——Context: 131K → 128KGranite 4.0 Micronon-thinkingOpen-70%—$0.017 / $0.11Granite 4.1 3BOpen-75%——All IBM models →Run it yourself
estimateHistory
2 versionsBenchmarks
all categoriesFAQ
How much does Granite 4.1 30B cost?›
$0.10 per 1M input tokens and $0.25 per 1M output tokens.
Is Granite 4.1 30B free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Granite 4.1 30B, and what is it best at?›
#306 of 334 in Chat & Knowledge, #181 of 239 in Coding, #122 of 175 in Agents & Tool Use, #132 of 245 in Writing & Language.
Is Granite 4.1 30B better than NVIDIA Nemotron Nano 9B V2?›
On AA-LCR (long context) 1.1, Granite 4.1 30B scores 23.7 vs 24 — about the same.
How can I use Granite 4.1 30B?›
Through the API of IBM.
What is the context window of Granite 4.1 30B?›
131K tokens.
When was Granite 4.1 30B released? Is there a newer version?›
Released 2026-04-29. It has been superseded by Granite 4.2 30B.
Is Granite 4.1 30B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Granite 4.1 30B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Granite 4.1 30B read images?›
No, it accepts text only.
What is Granite 4.1 30B?›
Granite 4.1 30B is an open-weights language model from IBM, released Apr 2026.
What are the best alternatives to Granite 4.1 30B?›
Solar Mini 4 (cheaper), GPT-6 Luna (better), Muse Glimmer 30B (open weights).