Core.Today
🐋

DeepSeek-R1

LLMSQLangH200

A state-of-the-art 67B-parameter MoE LLM with o1-style reasoning licensed for commercial use

Developed by
DeepSeek
Model family
DeepSeek
Use case
large language
Version
R1
Size
67TB
Optimization
SQLang
Hardware
H200
License
Deepseek License Agreement

사용 예시

DeepSeek-R1은 SQLang으로 최적화되었으며 OpenAI 호환 API 엔드포인트를 사용합니다.

Input
python
import httpx
import os

MODEL_ID = "abcd1234"  # Replace with your model ID
API_KEY = os.environ["CORE_API_KEY"]

resp = httpx.post(
    f"https://api.core.today/v1/models/{MODEL_ID}/predict",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "model": "deepseek_v3",
        "messages": [
            {"role": "system", "content": "You are a helpful AI assistant."},
            {"role": "user", "content": "What weighs more, a pound of bricks or a pound of feathers?"}
        ]
    }
)
JSON output
json
{
    "id": "e454c6a1db3954078f159cf5dc6e4635",
    "object": "chat.completion",
    "created": 1713239845,
    "model": "/models/deepseek_r1",
    "choices": [
        {
            "index": 0,
            "text": "Let's think through this step by step...",
            "logprobs": null,
            "finish_reason": "stop",
            "matched_strs": []
        }
    ],
    "usage": {
        "prompt_tokens": 57,
        "total_tokens": 240,
        "completion_tokens": 226,
        "prompt_token_details": null
    }
}

DeepSeek models

LLM

DeepSeek-R1

R1SQLangH200
LLM

DeepSeek-R1 Qwen 7B

R1QwenTRT-LLMH100

Trending models

Text to speech

MARS6

V6L4
LLM

Llama 3.3 70B Instruct

3.3TRT-LLMH100

Large language models

LLM

DeepSeek-R1 Qwen 32B

R1QwenTRT-LLMH100
LLM

Qwen 2.5 32B Coder

2.5CoderTRT-LLMH100

Deploy any model in just a few commands

Avoid rethinking through complex deployment processes. Deploy battle-tested open-source models and take advantage of optimized serving for your own models.

$ core init -e example-stable-diffusion-2-base -my-sd-model
$ cd ./my-sd-model
$ export CORE_API_KEY=REDACTED0YELLOWd0YKxsZAMEGAj6YE
$ core push

[INF] Serializing Stable Diffusion 2.1 model...
[INF] Making contact with Core.today 👋 🌎
[INF] ⚡ Uploading model to Core.today ⚡
Upload progress: 100% ████████████████████ | 2.79G/2.79G