Seedance 2.0 Mini is live on viddly.io — video from $0.045/second 🚀
viddly.ioAI Model Gateway
API Market
DeepSeek

DeepSeek R2 API

Open reasoning model with visible chain of thought

Exposes its reasoning trace, which makes it useful where you need to audit how an answer was reached.

ChatTool useStreaming128K context

Quickstart

Authenticate with a bearer token from your dashboard, then POST the request below.

curl -X POST https://api.viddly.io/v1/chat/completions \
  -H "Authorization: Bearer $VIDDLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-r2",
    "messages": [
      {
        "role": "user",
        "content": "Explain retrieval augmented generation in two sentences."
      }
    ],
    "max_tokens": 512
  }'

Parameters

NameTypeDefaultDescription
messages*textChat messages array, OpenAI-compatible.
max_tokensnumber1024Upper bound on generated tokens.
temperaturenumber0.7Sampling temperature, 0–2.
streambooleanfalseStream tokens as server-sent events.

Similar models