A lightweight MoE language model optimized for computational efficiency, text generation, and agentic workflows. Designed for chatbots, AI agents, and long-context tasks with lower resource requirements.
1️⃣ Required setup (don’t skip this)
▪ Create an account: Sign up on the AI/ML API website (if you don’t have one yet).
▪ Generate an API key: In your account dashboard, create an API key and make sure it’s enabled in the UI.
2️ Copy the code example
At the bottom of this page, pick the snippet for your preferred programming language (Python / Node.js) and copy it into your project.
3️ Update the snippet for your use case
▪ Insert your API key: replace <YOUR_AIMLAPI_KEY> with your real AI/ML API key.
▪ Select a model: set the model field to the model you want to call.
▪ Provide input: fill in the request input field(s) shown in the example (for example, messages for chat/LLM models, or other inputs for image/video/audio models).
4️ (Optional) Tune the request
Depending on the model type, you can add optional parameters to control the output (e.g., generation settings, quality, length, etc.). See the API schema below for the full list.
5️ Run your code
Run the updated code in your development environment. Response time depends on the model and request size, but simple requests typically return quickly.
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_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
tool_choiceany ofOptional
Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
none is the default when no tools are present. auto is the default if tools are present.
string · enumOptional
none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools.
Possible values:
or
or
or
or
parallel_tool_callsbooleanOptional
Whether to enable parallel function calling during tool use.
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.
stopany ofOptional
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
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.
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.
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.
response_formatone ofOptional
An object specifying the format that the model must output.
or
or
echobooleanOptional
If True, the response will contain the prompt. Can be used with logprobs to return prompt logprobs.
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.
top_anumber · max: 1Optional
Alternate top sampling parameter.
repetition_penaltynumber · nullableOptional
A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition.
{
"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": "nvidia/nemotron-3-nano-30b-a3b",
"usage": {
"prompt_tokens": 137,
"completion_tokens": 914,
"total_tokens": 1051,
"completion_tokens_details": null,
"prompt_tokens_details": null
},
"meta": {
"usage": {
"credits_used": 120000,
"usd_spent": 0.06
}
}
}
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":"nvidia/nemotron-3-nano-30b-a3b",
"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: 'nvidia/nemotron-3-nano-30b-a3b',
messages:[
{
role:'user',
content: 'Hi! What do you think about mankind?' // insert your prompt here
}
],
}),
});
const data = await response.json();
console.log(JSON.stringify(data, null, 2));
}
main();
{
"id": "gen-1778117281-ppABz4UAkgEvlBXvPZuS",
"object": "chat.completion",
"created": 1778117281,
"model": "nvidia/nemotron-3-nano-30b-a3b",
"system_fingerprint": null,
"choices": [
{
"index": 0,
"logprobs": null,
"finish_reason": "stop",
"native_finish_reason": "stop",
"message": {
"role": "assistant",
"content": "I’ll answer with a take that leans on a mix of observation, history, and a bit of philosophical reflection—nothing “right” or “wrong,” just one way of looking at it.\n\n---\n\n## 1. **What makes humanity remarkable**\n\n| Aspect | Why it’s striking |\n|--------|-------------------|\n| **Creativity & Tool‑making** | From stone tools to quantum computers, we continuously devise new ways to reshape our environment. Art, music, storytelling, and humor are uniquely human ways of processing experience and sharing meaning. |\n| **Self‑reflection** | We can ask “Why am I here?” and “What does it all mean?” That meta‑awareness drives philosophy, science, and religion, and it gives us the capacity for both humility and aspiration. |\n| **Co‑operation on a massive scale** | We build societies that can coordinate millions of people—languages, laws, economies, and international treaties—allowing projects like eradicating smallpox or building the International Space Station. |\n| **Adaptability** | Humans thrive in deserts, tundras, underwater habitats, and even micro‑gravity. Our biological flexibility (including cultural adaptation) lets us survive where most other species would perish. |\n\n---\n\n## 2. **The darker / problematic side**\n\n| Issue | What it reveals |\n|-------|-----------------|\n| **Capacity for harm** | Our intellect is matched by the ability to design weapons of mass destruction, cause ecological collapse, or exploit one another on a systemic level. This paradox—powerful cognition paired with moral blind spots—is a central tension in human history. |\n| **Pattern of domination** | From empires to colonial enterprises, there’s a recurrent theme of using knowledge and technology to subjugate or exploit others, often justifying it with ideology or “civilizing” narratives. |\n| **Short‑term thinking** | Many of our collective crises (climate change, biodiversity loss, unsustainable debt) stem from prioritizing immediate gains—profit, political power—over long‑term stewardship. |\n| **Tribalism** | Our ability to form tight‑knit groups can also lead to “in‑group” bias, prejudice, and conflict with “out‑groups.” This is both an evolutionary adaptation for survival and a source of many modern social problems. |\n\n---\n\n## 3. **A dialectical view**\n\n* **Thesis:** Humanity creates tools, cultures, and systems that expand our possibilities. \n* **Antithesis:** The same tools can become weapons or sources of inequality, leading to self‑inflicted crises. \n* **Synthesis:** The next stage of human development is likely to involve **meta‑cognition and ethical coordination**—using our reflective capacities to align our technological power with a more equitable, sustainable vision of the future.\n\nIn other words, the binary of “good vs. bad” is too simplistic; humanity is a **dynamic process** where progress and regression are intertwined. When we collectively recognize the pitfalls (e.g., climate inaction, widening wealth gaps) and channel our ingenuity toward solutions, we can tip the balance toward a more constructive trajectory.\n\n---\n\n## 4. **What might help shift the balance?**\n\n1. **Collective storytelling that emphasizes shared vulnerability** \n Narrative empathy can reduce tribalism and encourage policies that benefit the planet as a whole.\n\n2. **Institutional reforms that embed long‑term thinking** \n Examples include independent climate courts, intergenerational budgets, and AI governance frameworks that prioritize safety and fairness.\n\n3. **Education that blends STEM with ethics and the humanities** \n Teaching critical thinking alongside moral philosophy nurtures the habit of asking “not just ‘can we?’ but ‘should we?’”\n\n4. **Technology that is co‑designed with communities** \n When tools are built *with* the people they serve—rather than *for* them—the outcomes tend to be more equitable and less coercive.\n\n---\n\n## 5. **A personal takeaway**\n\nIf I had to sum it up in one sentence: **Humanity is a paradox‑rich species capable of extraordinary creation and equally profound self‑sabotage; our future will be shaped by whether we can marshal our ingenuity toward inclusive, long‑term stewardship of ourselves and the planet.**\n\n---\n\n**Bottom line:** \nHumanity is a work in progress—a tapestry woven from moments of brilliance and blunders. By acknowledging both the luminous achievements and the shadows we cast, we can better navigate the path ahead. What we *think* about humanity matters less than what we *do* with that understanding. If we choose to act wisely, the best chapters of the human story are still unwritten.",
"refusal": null,
"reasoning": "The user asks a philosophical question. There's no disallowed content. It's a safe open-ended question. We can respond with a thoughtful reflection on humanity, acknowledging complexity, achievements, challenges. Need to be respectful, no political persuasion issues. Provide nuanced answer.\n",
"reasoning_details": [
{
"type": "reasoning.text",
"text": "The user asks a philosophical question. There's no disallowed content. It's a safe open-ended question. We can respond with a thoughtful reflection on humanity, acknowledging complexity, achievements, challenges. Need to be respectful, no political persuasion issues. Provide nuanced answer.\n",
"format": "unknown",
"index": 0
}
]
}
}
],
"usage": {
"completion_tokens": 1062,
"prompt_tokens": 25,
"total_tokens": 1087,
"completion_tokens_details": {
"reasoning_tokens": 74,
"image_tokens": 0,
"audio_tokens": 0
},
"prompt_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0,
"audio_tokens": 0,
"video_tokens": 0
}
},
"meta": {
"usage": {
"credits_used": 518,
"usd_spent": 0.000259
}
}
}
