All AI models · LLM benchmarks · Methodology

Thinking Machines

Inkling Small Thinking

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

Model facts

Context window
524K tokens
Maximum output
33K tokens
Cheapest paid input
$0.5 per 1M tokens
Cheapest paid output
$1.2 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.5 input / $1.2 output per 1M tokens

API providers

  • NanoGPT — model id thinkingmachines/Inkling-Small:thinking; $0.5 input / $1.2 output per 1M tokens; provider documentation