Gemma 4 31B
Gemma 4 31BAlternatives?
CheaperGemma 4 12BthinkingOpen-3%-6%$0.10 / $0.30
BetterMiMo v2.5 ProthinkingOpen+6%+240%$0.054Memory (4-bit): 19 GB → 614 GB+1
OpenNemotron Cascade 2 30B A3B+6%——No image inputCheaperNemotron 3 Nano 30B A3BthinkingOpen-6%-34%$0.017Context: 256K → 131K+1
CheaperGPT OSS 120BhighOpen-9%-63%$0.092Context: 256K → 131K+2Gemma 4 12BthinkingOpen-3%-6%$0.10 / $0.30Nemotron 3 Nano 30B A3BthinkingOpen-6%-34%$0.017Context: 256K → 131K+1GPT OSS 120BhighOpen-9%-63%$0.092Context: 256K → 131K+2GPT-5 Nanohigh-11%-14%$0.05 / $0.40
Qwen 3.5 9BthinkingOpen-12%-42%$0.21MiMo v2.5 ProthinkingOpen+6%+240%$0.054Memory (4-bit): 19 GB → 614 GB+1
Grok 4.3high+8%+877%$0.21Qwen3.7 Plusthinking+3%+250%$0.22Qwen3.5 397B A17BthinkingOpen+4%+744%$0.47Memory (4-bit): 19 GB → 242 GB
MiniMax M3thinkingOpen+10%+228%$0.51Memory (4-bit): 19 GB → 256 GB+2Nemotron Cascade 2 30B A3BOpen+6%——No image inputQwen 3.5 27BthinkingOpensame+416%$0.30 / $2.40Gemma 4 12BthinkingOpen-3%-6%$0.10 / $0.30Qwen 3.5 35B A3BthinkingOpen-4%+330%$0.25 / $2Memory (4-bit): 19 GB → 22 GBGemma 4 26B A4BthinkingOpen-4%+64%$0.15 / $0.60Gemini 3.1 Flash Litehigh+2%—$0.06Gemini 3.1 Pro Previewthinking+2%—$1.30Cannot use both thinking controlsGemma 4 12BthinkingOpen-3%—$0.10 / $0.30Gemma 4 26B A4BthinkingOpen-4%—$0.15 / $0.60DiffusionGemma 26B A4BOpen-21%—$0.05 / $0.15Gemini 3 Flash Previewnon-thinking-27%—$0.50 / $3Gemini 2.5 Prothinking-36%—$0.33Gemma 4 E4BthinkingOpen-41%—$0.008Context: 256K → 128KAll Google models →Run it yourself
estimateBenchmarks
in Writing & LanguageFAQ
How much does Gemma 4 31B cost?›
$0.10 per 1M input tokens and $0.34 per 1M output tokens (cheapest host: CoreWeave).
Is Gemma 4 31B 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 Gemma 4 31B, and what is it best at?›
#105 of 334 in Chat & Knowledge, #75 of 132 in Coding, #85 of 133 in Agents & Tool Use, #55 of 195 in Writing & Language, #61 of 124 in Vision & Documents. Strongest at: Science, Instructions.
Is Gemma 4 31B better than Qwen 3.5 122B A10B?›
On IFBench (instructions), Gemma 4 31B scores 75.6 vs 75.7 — about the same.
How can I use Gemma 4 31B?›
Through the API of Chutes, CoreWeave, Crusoe, DeepInfra, Featherless and 7 more.
What is the context window of Gemma 4 31B?›
256K tokens, with up to 33K output tokens.
When was Gemma 4 31B released? Is there a newer version?›
Released 2026-04-02. It is the current version in its line.
Is Gemma 4 31B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Gemma 4 31B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 4 31B read images?›
It accepts text and images, video as input.
What is Gemma 4 31B?›
Gemma 4 31B is an open-weights language model from Google, released Apr 2026.
What are the best alternatives to Gemma 4 31B?›
Gemma 4 12B (cheaper), MiMo v2.5 Pro (better), Nemotron Cascade 2 30B A3B (open weights).