Let's build something great today.

Here, you can discover production-ready AI models developed by Upstage, to build your applications with ease. If you're looking to leverage LLMs for complex document tasks—such as building a document QA service or extracting key information—you’ve come to the right place. Concerned about privacy? Rest assured, we do not store or reuse any data sent to our APIs. For more details, check our terms.

Start building

To sign up, press the Log in button at the upper right of this page.

Get an API key

To get an API key, just click the Create new key below. You can view keys in the API keys page.

Make an API request

Choose a capability from the menu and make an API request using the provided example code. Each capability includes a ready-to-use code snippet. For AI agents, use the machine-readable docs index at /llms.txt.

Example codes

from openai import OpenAI

client = OpenAI(
    api_key="UPSTAGE_API_KEY",
    base_url="https://api.upstage.ai/v1"
)

response = client.chat.completions.create(
    model="solar-pro4",
    messages=[
        {
            "role": "user",
            "content": "An $80 item gets a 20% discount, then 10% tax is added. What is the final price? Answer with only the dollar amount."
        }
    ],
    reasoning_effort="medium"
)

message = response.choices[0].message

reasoning = getattr(message, "reasoning", None)
if reasoning:
    print(reasoning)

print(message.content)

Explore our offerings

Upstage provides a diverse range of AI capabilities, each designed to address specific needs across various workflows.

Agent

Build autonomous AI agents that can complete complex tasks.

Chat

Chat with a family of small yet powerful LLMs.

Document parsing

Convert complex documents into LLM-readable formats.

Information extraction

Extract key-values from target documents with high precision.

Document classification

Classify documents into predefined categories.

Embeddings

Convert text to vector representations for advanced search applications.

Have questions?

Please visit the following resources for assistance!

from openai import OpenAI

client = OpenAI(
    api_key="UPSTAGE_API_KEY",
    base_url="https://api.upstage.ai/v1"
)

response = client.chat.completions.create(
    model="solar-pro4",
    messages=[
        {
            "role": "user",
            "content": "An $80 item gets a 20% discount, then 10% tax is added. What is the final price? Answer with only the dollar amount."
        }
    ],
    reasoning_effort="medium"
)

message = response.choices[0].message

reasoning = getattr(message, "reasoning", None)
if reasoning:
    print(reasoning)

print(message.content)

Explore our offerings

Upstage provides a diverse range of AI capabilities, each designed to address specific needs across various workflows.

Agent

Build autonomous AI agents that can complete complex tasks.

Chat

Chat with a family of small yet powerful LLMs.

Document parsing

Convert complex documents into LLM-readable formats.

Information extraction

Extract key-values from target documents with high precision.

Document classification

Classify documents into predefined categories.

Embeddings

Convert text to vector representations for advanced search applications.

Have questions?

Please visit the following resources for assistance!

Let's build something great today.

Start building

Get an API key

Make an API request

Explore our offerings

Have questions?

On this page

Let's build something great today.

Start building

Get an API key

Make an API request

Explore our offerings

Have questions?

On this page