Text generation

To generate text with an LLM, you need to use the chat completions API. This API allows you to send text, images, and videos with your request, using an OpenAI-compatible interface, as shown in the following examples. The examples below use the minimax-m3 model, but you can replace it with any supported model that’s listed as an “LLM” type.

Requirements

An API key. The code below assumes you set it in an environment variable:
export MODULAR_API_KEY="your_api_key"
$env:MODULAR_API_KEY="your_api_key"
The openai Python package. You can install it with this command:
pip install openai
uv add openai
pixi add openai
npm install openai

Generate a text response

Here’s how you can generate text from a prompt or conversation history.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key=os.environ.get("MODULAR_API_KEY"),
)

response = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
        {"role": "assistant", "content": "The LA Dodgers won in 2020."},
        {"role": "user", "content": "Where was it played?"}
    ]
)
print(response.choices[0].message.content)

import process from "node:process";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.modular.com/v1",
  apiKey: process.env.MODULAR_API_KEY,
});

async function main() {
  const response = await client.chat.completions.create({
    model: "minimax/minimax-m3",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Who won the world series in 2020?" },
      { role: "assistant", content: "The LA Dodgers won in 2020." },
      { role: "user", content: "Where was it played?" },
    ],
  });

  console.log(response.choices[0].message.content);
}

main();

curl -X POST https://api.modular.com/v1/chat/completions \
  -H "Authorization: Bearer $MODULAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Who won the world series in 2020?"},
      {"role": "assistant", "content": "The LA Dodgers won in 2020."},
      {"role": "user", "content": "Where was it played?"}
    ]
  }'

Stream a text response

Set stream=True to receive tokens as they are generated instead of waiting for the full response.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key=os.environ.get("MODULAR_API_KEY"),
)

stream = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[{"role": "user", "content": "Write a short poem about the sea."}],
    stream=True,
)

for chunk in stream:
    if not chunk.choices:
        continue
    content = chunk.choices[0].delta.content
    if content is not None:
        print(content, end="", flush=True)
print()

import process from "node:process";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.modular.com/v1",
  apiKey: process.env.MODULAR_API_KEY,
});

async function main() {
  const stream = await client.chat.completions.create({
    model: "minimax/minimax-m3",
    messages: [{ role: "user", content: "Write a short poem about the sea." }],
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
  }
  process.stdout.write("\n");
}

main();

curl -X POST https://api.modular.com/v1/chat/completions \
    -H "Authorization: Bearer $MODULAR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "minimax/minimax-m3",
      "messages": [{"role": "user", "content": "Write a short poem about the sea."}],
      "stream": true
    }'

Analyze an image

Some LLMs accept images, allowing them to generate a description or analysis of the image visual content. You can use any supported model that’s both an “LLM” and a “Vision” type. To pass an image, add the image_url attribute in the messages.content object. The inner url attribute accepts either a publicly accessible URL or a base64-encoded data URI (for example, data:image/jpeg;base64,...). Notice that content is an array, allowing you to pass multiple images at once.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key=os.environ.get("MODULAR_API_KEY"),
)

response = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
                    },
                },
            ],
        }
    ],
    max_tokens=300,
)

print(response.choices[0].message.content)

import process from "node:process";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.modular.com/v1",
  apiKey: process.env.MODULAR_API_KEY,
});

async function main() {
  const response = await client.chat.completions.create({
    model: "minimax/minimax-m3",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "text",
            text: "What is in this image?",
          },
          {
            type: "image_url",
            image_url: {
              url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg",
            },
          },
        ],
      },
    ],
    max_tokens: 300,
  });

  console.log(response.choices[0].message.content);
}

main();

curl -X POST https://api.modular.com/v1/chat/completions \
  -H "Authorization: Bearer $MODULAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m3",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d '\n' | sed 's/\\n/\n/g'

Analyze a video

Some LLMs accept video input, allowing them to generate a description or analysis of the video’s visual content. You can use any supported model that’s both an “LLM” and a “Vision” type. To pass a video, add the video_url attribute in the messages.content object. The inner url attribute accepts either a publicly accessible URL or a base64-encoded data URI (for example, data:video/mp4;base64,...). Notice that content is an array, allowing you to pass multiple videos at once, or even a combination of videos and images.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key=os.environ.get("MODULAR_API_KEY"),
)

completion = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe what is happening in this video"},
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://avtshare01.rz.tu-ilmenau.de/avt-vqdb-uhd-1/test_1/segments/bigbuck_bunny_8bit_15000kbps_1080p_60.0fps_h264.mp4"
                    },
                },
            ],
        }
    ],
    max_tokens=300,
    # minimax-m3 uses adaptive thinking by default, which can consume the entire
    # token budget when analyzing videos, leaving message.content empty.
    extra_body={"reasoning": {"enabled": False}},
)

print(completion.choices[0].message.content)

import process from "node:process";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.modular.com/v1",
  apiKey: process.env.MODULAR_API_KEY,
});

async function main() {
  const response = await client.chat.completions.create({
    model: "minimax/minimax-m3",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "text",
            text: "Describe what is happening in this video",
          },
          {
            type: "video_url",
            video_url: {
              url: "https://avtshare01.rz.tu-ilmenau.de/avt-vqdb-uhd-1/test_1/segments/bigbuck_bunny_8bit_15000kbps_1080p_60.0fps_h264.mp4",
            },
          },
        ],
      },
    ],
    max_tokens: 300,
    // minimax-m3 uses adaptive thinking by default, which can consume the entire
    // token budget when analyzing videos, leaving message.content empty.
    reasoning: { enabled: false },
  } as OpenAI.Chat.Completions.ChatCompletionCreateParamsNonStreaming);

  console.log(response.choices[0].message.content);
}

main();

curl -X POST https://api.modular.com/v1/chat/completions \
  -H "Authorization: Bearer $MODULAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m3",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Describe what is happening in this video"
          },
          {
            "type": "video_url",
            "video_url": {
              "url": "https://avtshare01.rz.tu-ilmenau.de/avt-vqdb-uhd-1/test_1/segments/bigbuck_bunny_8bit_15000kbps_1080p_60.0fps_h264.mp4"
            }
          }
        ]
      }
    ],
    "max_tokens": 300,
    "reasoning": {"enabled": false}
  }' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d '\n' | sed 's/\\n/\n/g'

Get started

Inference

Administration

Integrations

Requirements

Generate a text response

Stream a text response

Analyze an image

Analyze a video

​Requirements

​Generate a text response

​Stream a text response

​Analyze an image

​Analyze a video

Requirements

Generate a text response

Stream a text response

Analyze an image

Analyze a video