← Back to Directory

Thinking Machines: Inkling (batch)

THINKINGMACHINES Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1423Chatbot Arena Verified
Max Context524,288Tokens
API Cost / 1M$2.52Blended Prompt + Completion

Model Capabilities

  • Audio Gen
  • Coding & Logic
  • Fictional
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Granular Pricing Matrix

Input Tokens (Prompt)$0.50 / 1M
Output Tokens (Completion)$2.02 / 1M

Pricing data via OpenRouter. Sync: 8/6/2026

Evaluate Competitors

VS Engine MatchupThinking Machines: Inkling (batch) vs Qwen: Qwen3.5 Plus 2026-04-20VS Engine MatchupThinking Machines: Inkling (batch) vs Qwen: Qwen3.5 Plus 2026-02-15VS Engine MatchupThinking Machines: Inkling (batch) vs Anthropic: Claude Haiku 4.5 (batch)VS Engine MatchupThinking Machines: Inkling (batch) vs Relace: Relace Apply 3VS Engine MatchupThinking Machines: Inkling (batch) vs Qwen: Qwen3 Next 80B A3B ThinkingVS Engine MatchupThinking Machines: Inkling (batch) vs Mistral: Mistral Medium 3