Home / Models / Plugsky Reasoning

Plugsky Reasoning API

Plugsky Reasoning: 550B (activated: ~55B), 262144 token serving context. Equivalent class and context required on failover.

Context window
262,144 tokens
Max output
16,384 tokens
Parameters
550B (activated: ~55B)
Input
text
Plan
Paid plans

Capabilities

chatstreamingreasoningtoolsjson modelong context

Call it

curl https://plugsky.com/v1/chat/completions \
  -H "Authorization: Bearer $PLUGSKY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "plugsky-reasoning", "messages": [{"role": "user", "content": "Say hello in five words."}]}'

OpenAI-compatible. Point any OpenAI SDK at https://plugsky.com/v1 and use plugsky-reasoning as the model.

Typical workloads

Related models

Ready to call Plugsky Reasoning?

One endpoint, 39 models, flat-rate plans. Free tier to start.

Start freeSee plans