All AI models · LLM benchmarks · Methodology

Stealth: Qwen3.6 Plus (50% off)

Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.

Model facts

Context window
1M tokens
Maximum output
66K tokens
Cheapest paid input
$0.25 per 1M tokens
Cheapest paid output
$1.5 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, attachments, temperature control, text, image.

Observed price history

  • 2026-08-24: $0.25 input / $1.5 output per 1M tokens

API providers

  • Kilo Gateway — model id stealth/qwen3.6-plus; $0.25 input / $1.5 output per 1M tokens; provider documentation