All AI models · LLM benchmarks · Methodology

Inkling (256K)

Inkling 256K is the extended context variant of Inkling, a large MoE hybrid reasoning model from Thinking Machines with audio and vision input support and a 256K context window.

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$1.87 per 1M tokens
Cheapest paid output
$4.68 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $1.5 input / $3.74 output per 1M tokens
  • 2026-08-28: $1.87 input / $4.68 output per 1M tokens

API providers

  • Requesty — model id inkling-256k; $1.87 input / $4.68 output per 1M tokens; provider documentation
  • Thinking Machines — model id thinkingmachines/Inkling:peft:262144; $3.74 input / $9.36 output per 1M tokens; provider documentation