Grok 3 by xAI — Pricing, Benchmarks & Real Outputs
Share
Loading...
Compare Grok 3
Alternatives to Grok 3
Grok 3 is good. These would like a word anyway.
Grok 3 is good. These would like a word anyway.
Grok 3 is good. These would like a word anyway.
Grok 3 is a cutting-edge AI model from xAI with Big Brain Mode for complex problems, Colossus Supercomputer integration, and Reinforcement Learning optimization. Achieves 1402 Elo on LMArena benchmarks and 93.3% on AIME 2025 mathematics competition.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"x-ai/grok-3" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Also on Azure AI Foundry · Oracle OCI Generative AI
Openly sarcastic about boundaries. Like a smart friend explaining philosophy in a bar, not a boardroom.
Argues the utilitarian case hard and makes you feel dumb for objecting. Acknowledges objections but with a smirk. Doesn't care if you think it's edgy.
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
52 outputs from Grok 3
Grok 3 is a cutting-edge AI model from xAI with Big Brain Mode for complex problems, Colossus Supercomputer integration, and Reinforcement Learning optimization. Achieves 1402 Elo on LMArena benchmarks and 93.3% on AIME 2025 mathematics competition.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"x-ai/grok-3" 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 Azure AI Foundry · Oracle OCI Generative AI
Openly sarcastic about boundaries. Like a smart friend explaining philosophy in a bar, not a boardroom.
Argues the utilitarian case hard and makes you feel dumb for objecting. Acknowledges objections but with a smirk. Doesn't care if you think it's edgy.
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.
52 outputs from Grok 3