Model reference · open weights

HyperCLOVAX-SEED-Think

Available as managed deployment Licence fee LLMs naver-hyperclovax Text gen 1 variants 13k dl/mo

HyperCLOVAX-SEED-Think is an open-weight language model from naver-hyperclovax. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bynaver-hyperclovax
TypeLanguage models
TaskText gen
Parameters (lead)33.3B
Context128k tokens
Runs withtransformers
Released2025-12-23
Popularity13k downloads / month
LicenceCommercial licence needed

About

What HyperCLOVAX-SEED-Think is

HyperCLOVA X SEED 32B Think is an updated vision-language thinking model that advances the SEED Think 14B line beyond simple scaling, pairing a unified vision-language Transformer backbone with a reasoning-centric training recipe. SEED 32B Think processes text tokens and visual patches within a shared embedding space, supports long-context multimodal understanding up to 128K tokens, and provides an optional “thinking mode” for deep, controllable reasoning. Building on the earlier 14B model, SEED 32B Think further strengthens Korean-centric reasoning and agentic capabilities, improving practical reasoning quality and reliability in real-world use.


Read the full model card

Technical Report


Basic Information

  • Architecture : Transformer-based vision-language model (VLM) architecture (Dense Model)
  • Parameters : 32B
  • Input Format: Text/Image/Video
  • Output Format: Text
  • Context Length : 128K
  • Knowledge Cutoff: May 2025

Benchmarks

  • General Knowledge (Korean Text): KoBalt, CLIcK, HAERAE Bench 1.0
  • Vision Understanding : ChartVQA, TextVQA, K-MMBench, K-DTCBench
  • Agentic Tasks: Tau^2-Airline, Tau^2-Retail, Tau^2-Telecom

Examples

  • Solving 2026 Korean CSAT Math Problem
  • Understanding Text layout

Inference

We provide OmniServe, a production-ready multimodal inference system with OpenAI-compatible API.

Capabilities

  • Inputs: Text, Image
  • Outputs: Text

Requirements

  • 4x NVIDIA A100 80GB
  • Docker & Docker Compose
  • NVIDIA Driver 525+, CUDA 12.1+

Installation

# Clone OmniServe
git clone https://github.com/NAVER-Cloud-HyperCLOVA-X/OmniServe.git
cd OmniServe

# Install dependencies
pip install huggingface_hub safetensors torch openai easydict

# Download model (~60GB)
huggingface-cli download naver-hyperclovax/HyperCLOVAX-SEED-Think-32B \
    --local-dir ./models/HyperCLOVAX-SEED-Think-32B

# Convert model to component format
python convert_model.py \
    --input ./models/HyperCLOVAX-SEED-Think-32B \
    --output ./track_a \
    --track a

# Configure environment
cp .env.example .env
# Edit .env:
# VLM_MODEL_PATH=./track_a/llm/HyperCLOVAX-SEED-Think-32B
# VLM_ENCODER_VISION_MODEL_PATH=./track_a/ve/HyperCLOVAX-SEED-Think-32B

# Build and run
docker compose --profile track-a build
docker compose --profile track-a up -d

# Wait for model loading (~5 minutes)
docker compose logs -f vlm

Basic Usage

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/a/v1",
    api_key="not-needed"
)

# Image understanding
response = client.chat.completions.create(
    model="track_a_model",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
                {"type": "text", "text": "Describe this image."}
            ]
        }
    ],
    max_tokens=512,
    extra_body={"chat_template_kwargs": {"thinking": False}}
)

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

Reasoning Mode

Enable chain-of-thought reasoning for complex tasks:

response = client.chat.completions.create(
    model="track_a_model",
    messages=[
        {"role": "user", "content": "Solve step by step: 3x + 7 = 22"}
    ],
    max_tokens=1024,
    extra_body={
        "thinking_token_budget": 500,
        "chat_template_kwargs": {"thinking": True}
    }
)

# Response includes ... with reasoning process
print(response.choices[0].message.content)

More Examples

response = client.chat.completions.create(
    model="track_a_model",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": "https://example.com/video.mp4"}},
                {"type": "text", "text": "Describe this video."}
            ]
        }
    ],
    max_tokens=512,
    extra_body={"chat_template_kwargs": {"thinking": False}}
)
import base64

with open("image.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="track_a_model",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_b64}"}},
                {"type": "text", "text": "What is in this image?"}
            ]
        }
    ],
    max_tokens=512,
    extra_body={"chat_template_kwargs": {"thinking": False}}
)
curl -X POST http://localhost:8000/a/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "track_a_model",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
          {"type": "text", "text": "Describe this image."}
        ]
      }
    ],
    "max_tokens": 512,
    "extra_body": {"chat_template_kwargs": {"thinking": false}}
  }'

Model Capabilities

InputOutput
TextText
ImageText
VideoText
Image + TextText
Video + TextText

Features:

  • Reasoning mode with ... output
  • Multi-turn conversation support
  • Image/Video understanding

Architecture

                         User Request
                       (Image/Video/Text)
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                            OmniServe                                    │
│                  POST /a/v1/chat/completions                            │
│                                                                         │
│  ┌────────────────────────────────────────────────

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys hyperclovax-seed-think for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hyperclovax-seed-think below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hyperclovax-seed-think","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms