Thinking Machines: Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

• Context window: 524,288 tokens
• Input: text, image, audio
• Output: text
• Pricing: $0.5/M input tokens, $1.2/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.