All AI models · LLM benchmarks · Methodology

thinkingcap-qwen3.6-27b

ThinkingCap-Qwen3.6-27B is a reasoning tuned model from BottlecapAI built on Qwen3.6 27B. It supports extended thinking with tool calling and a 256K context window. Served via Sference.

Model facts

Context window
262K tokens
Maximum output
33K tokens
Cheapest paid input
$0.4 per 1M tokens
Cheapest paid output
$3 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, text.

Observed price history

  • 2026-08-24: $0.36 input / $2.7 output per 1M tokens
  • 2026-08-28: $0.4 input / $3 output per 1M tokens

API providers