Google: Gemma 4 31B by Google AI — Pricing, Benchmarks & Real Outputs
Share
Loading...
Compare Google: Gemma 4 31B
Alternatives to Google: Gemma 4 31B
Google: Gemma 4 31B is good. These would like a word anyway.
Google: Gemma 4 31B is good. These would like a word anyway.
Google: Gemma 4 31B is good. These would like a word anyway.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"google/gemma-4-31b-it" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Also on NVIDIA NIM
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
44 outputs from Google: Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"google/gemma-4-31b-it" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Also on NVIDIA NIM
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
44 outputs from Google: Gemma 4 31B