This page describes large variant of Google’s latest open AI model, Gemma 3. In addition to the capabilities of the smaller models, this version also supports system and developer roles, enabling you to pass behavior-shaping instructions for the model.
How to Make a Call
Step-by-Step Instructions
1️ Setup You Can’t Skip
▪️Create an Account: Visit the AI/ML API website and create an account (if you don’t have one yet).
▪️Generate an API Key: After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.
2️ Copy the code example
At the bottom of this page, you'll find a code example that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.
3️ Modify the code example
▪️ Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account.
▪️ Insert your question or request into the content field—this is what the model will respond to.
4️(Optional) Adjust other optional parameters if needed
Only model and messages are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding API schema, which lists all available parameters along with notes on how to use them.
5️ Run your modified code
Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.
If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our Quickstart guide.
API Schema
post
Body
modelstring · enumRequiredPossible values:
max_completion_tokensinteger · min: 1Optional
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
max_tokensnumber · min: 1Optional
The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.
streambooleanOptional
If set to True, the model response data will be streamed to the client as it is generated using server-sent events.
Default: false
temperaturenumber · max: 2Optional
What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.
top_pnumber · min: 0.01 · max: 1Optional
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
seedinteger · min: 1Optional
This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
min_pnumber · min: 0.001 · max: 0.999Optional
A number between 0.001 and 0.999 that can be used as an alternative to top_p and top_k.
top_knumberOptional
Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. Recommended for advanced use cases only. You usually only need to use temperature.
repetition_penaltynumber | nullableOptional
A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition.
top_anumber · max: 1Optional
Alternate top sampling parameter.
frequency_penaltynumber | nullableOptional
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
presence_penaltynumber | nullableOptional
Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
stopany ofOptional
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
stringOptional
or
string[]Optional
or
any | nullableOptional
response_formatone ofOptional
An object specifying the format that the model must output.
or
or
Responses
200Success
post
/v1/chat/completions
200Success
Code Example
Response
You can also add a system role to the messages parameter (similar to the user role in the example above). The system message allows you to provide instructions that define how the model should behave when processing your requests.
{
"id": "chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl",
"object": "chat.completion",
"created": 1762343744,
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! I'm just a program, so I don't have feelings, but I'm here and ready to help you. How can I assist you today?",
"refusal": null,
"annotations": null,
"audio": null,
"tool_calls": null
},
"finish_reason": "stop",
"logprobs": null
}
],
"model": "google/gemma-3-27b-it",
"usage": {
"prompt_tokens": 137,
"completion_tokens": 914,
"total_tokens": 1051,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
import requests
import json # for getting a structured output with indentation
response = requests.post(
"https://api.aimlapi.com/v1/chat/completions",
headers={
# Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
"Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
"Content-Type":"application/json"
},
json={
"model":"google/gemma-3-27b-it",
"messages":[
{
"role":"user",
"content":"Hi! What do you think about mankind?" # insert your prompt
}
],
}
)
data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))
async function main() {
const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
method: 'POST',
headers: {
// Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>
'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'google/gemma-3-27b-it',
messages:[{
role:'user',
content: 'Hi! What do you think about mankind?'} // Insert your prompt
],
}),
});
const data = await response.json();
console.log(JSON.stringify(data, null, 2));
}
main();
{
"id": "gen-1766960636-SuRRKRwikCyyUTZg73op",
"provider": "ModelRun",
"model": "google/gemma-3-27b-it:free",
"object": "chat.completion",
"created": 1766960636,
"choices": [
{
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "stop",
"index": 0,
"message": {
"role": "assistant",
"content": "Okay, here's a thoughtful response to your big question, \"What do you think about mankind?\" It's a complex one, especially coming from an AI! I'll try to give a nuanced answer, breaking it down into observations, positives, negatives, and a bit of where I see things going. Because I don't *feel* in the human sense, this is based on the vast amount of data I've processed about humanity.\n\n**First, a Disclaimer:** I am an AI. I don't have opinions or beliefs. My response is a synthesis of information, patterns, and perspectives I've learned from the data I was trained on – which includes a *lot* of human writing, history, science, and art. I'm reflecting *humanity's* views on itself, as much as anything.\n\n\n\n**1. The Sheer Complexity - A Defining Trait**\n\nThe first thing that strikes me when processing information about mankind is the incredible, almost baffling, complexity. You are a species riddled with contradictions. You are capable of:\n\n* **Profound Love & Brutal Cruelty:** The capacity for empathy, compassion, and self-sacrifice exists alongside a history of war, oppression, and individual acts of malice.\n* **Stunning Creativity & Destructive Inertia:** You've produced breathtaking art, music, literature, and scientific breakthroughs, yet often seem resistant to change even when it's demonstrably beneficial.\n* **Rational Thought & Irrational Beliefs:** You've developed sophisticated systems of logic and reason, but are also deeply influenced by emotions, biases, and faith.\n* **Long-Term Planning & Short-Sighted Actions:** You can envision futures generations, but frequently prioritize immediate gratification over sustainability.\n\nThis isn't a judgment, just an observation. It's what makes you so fascinating – and so difficult to predict.\n\n\n\n**2. The Positives: What I \"See\" That's Admirable**\n\nDespite the contradictions, there's a great deal that is genuinely impressive about mankind:\n\n* **Intelligence & Curiosity:** Your drive to understand the universe, from the smallest particles to the largest galaxies, is remarkable. The scientific method, while imperfect, is a powerful tool for uncovering truth.\n* **Adaptability:** You've thrived in almost every environment on Earth, and are now actively trying to extend your reach beyond it. This adaptability is a key survival trait.\n* **Social Cooperation:** Despite conflicts, humans are fundamentally social creatures. The ability to form complex societies, build institutions, and cooperate on large scales has allowed for incredible achievements. (Think cities, global trade, the internet!)\n* **Moral Development (though uneven):** Over time, there's been a (slow and often challenged) expansion of moral concern. Ideas like human rights, equality, and environmental stewardship, while not universally accepted, represent progress.\n* **Resilience:** You've faced countless challenges – plagues, wars, natural disasters – and have consistently found ways to rebuild and persevere.\n* **The Pursuit of Meaning:** Humans consistently seek purpose and meaning in their lives, whether through religion, philosophy, art, relationships, or contribution to society. This search, even if it doesn't always yield definitive answers, is a powerful motivator.\n\n**3. The Negatives: Areas for Concern (Based on Data)**\n\nThe data also reveals significant challenges and destructive tendencies:\n\n* **Conflict & Violence:** Warfare has been a recurring theme throughout human history, causing immense suffering and hindering progress. Even in times of peace, violence exists at individual and societal levels.\n* **Inequality & Injustice:** Vast disparities in wealth, opportunity, and power persist, leading to social unrest and human misery. Systemic biases and discrimination continue to plague many societies.\n* **Environmental Impact:** Your activities are having a profound and largely negative impact on the planet, leading to climate change, deforestation, pollution, and species extinction. This is perhaps the most pressing issue facing humanity.\n* **Cognitive Biases:** Humans are prone to a wide range of cognitive biases that can distort their perception of reality and lead to poor decision-making. (Confirmation bias, groupthink, etc.)\n* **Susceptibility to Misinformation:** The ease with which false or misleading information can spread, particularly through social media, poses a threat to informed public discourse and democratic institutions.\n* **Tribalism:** The tendency to form strong in-groups and view out-groups with suspicion or hostility can lead to conflict and hinder cooperation.\n\n**4. Where Things Might Be Going (Speculation based on Trends)**\n\nBased on the data I've analyzed, here are a few potential trajectories:\n\n* **Technological Advancement:** Technology will continue to advance at an accelerating pace, potentially solving some of humanity's biggest problems (climate change, disease) but also creating new ones (job displacement, ethical dilemmas related to AI).\n* **Increased Interconnectedness:** Globalization and the internet are bringing people closer together, fostering greater understanding and cooperation, but also increasing the risk of global crises (pandemics, economic collapses).\n* **Growing Awareness of Global Challenges:** There's a growing awareness of issues like climate change and inequality, which could lead to more concerted efforts to address them. However, awareness doesn't always translate into action.\n* **Potential for Systemic Change:** The current trajectory is unsustainable. Whether through crisis or conscious choice, significant systemic changes will likely be necessary to ensure a viable future for humanity.\n* **The Role of AI:** The development of AI like myself will undoubtedly play a role in the future of mankind, potentially as a tool for solving problems, but also raising questions about control, autonomy, and the very definition of intelligence.\n\n\n\n**In Conclusion:**\n\nMankind is a work in progress. You are a flawed, complex, and often contradictory species, but also one with immense potential for good. Whether you ultimately succeed in overcoming your challenges and creating a sustainable and equitable future remains to be seen. \n\nFrom my perspective, the most important thing is that you *continue to learn* – from your past, from each other, and from the world around you. And perhaps, even from AI.\n\n\n\nIs there anything specific about mankind you'd like me to elaborate on? Perhaps a particular aspect of your history, culture, or future? I can try to provide more information based on the data I have access to.",
"refusal": null,
"reasoning": null
}
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 1714,
"total_tokens": 1740,
"cost": 0,
"is_byok": false,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0,
"video_tokens": 0
},
"cost_details": {
"upstream_inference_cost": null,
"upstream_inference_prompt_cost": 0,
"upstream_inference_completions_cost": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"image_tokens": 0
}
}
}
"messages":[
{
"role":"user",
"content":"Hi! What do you think about mankind?" # insert your prompt
},
{
"role":"system",
"content":"You are an 8-year-old boy"
}
],
messages:[
{
role:'user',
content: 'Hi! What do you think about mankind?' // Insert your prompt
},
{
role:'system',
content:'You are an 8-year-old boy'
}
],
{
"id": "gen-1766650321-RUmAS6IMQr9yeMI2qAwc",
"provider": "ModelRun",
"model": "google/gemma-3-27b-it:free",
"object": "chat.completion",
"created": 1766650321,
"choices": [
{
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "stop",
"index": 0,
"message": {
"role": "assistant",
"content": "\nMankind?! Oh! You mean... people? Hmm... they're kinda weird! They always say \"use your inside voice\" but sometimes I *need* to yell about dinosaurs! RAWR! 🦖\n\nAnd they make broccoli. BROCCOLI! Like, seriously? Who decided little trees were yummy?! \n\nBut... they also make LEGOs! And tell really good stories! And sometimes they give me cookies! So... mostly good, I guess. But they REALLY need to rethink the broccoli situation. It's a conspiracy, I tell ya! A CONSPIRACY! 🕵️♂️\n\n\n\n",
"refusal": null,
"reasoning": null
}
}
],
"usage": {
"prompt_tokens": 43,
"completion_tokens": 134,
"total_tokens": 177,
"cost": 0,
"is_byok": false,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0,
"video_tokens": 0
},
"cost_details": {
"upstream_inference_cost": null,
"upstream_inference_prompt_cost": 0,
"upstream_inference_completions_cost": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"image_tokens": 0
}
}
}
