Thinking Machines: Inkling
THINKINGMACHINES Developer Architecture Profile
Intelligence (ELO)1460Chatbot Arena Verified
Max Context Limit524,288Max Out: 262,144 tokens
Prompt Caching83% OFF$0.16 / 1M cached
Standard API / 1M$5.00🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Audio Gen
- Reasoning
- Coding & Logic
- Fictional
- 🧠 Extended Test-Time Reasoning
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 (Standard Prompt)$0.95 / 1M
⚡ Cached Input (Prompt Cache Read)83% OFF$0.16 / 1M
Output Tokens (Completion)$4.05 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupThinking Machines: Inkling vs Meta: Muse Spark 1.2VS Engine MatchupThinking Machines: Inkling vs Amazon: Nova Pro 1.0VS Engine MatchupThinking Machines: Inkling vs OpenAI: GPT-6 Sol (batch)VS Engine MatchupThinking Machines: Inkling vs Meta: Muse Spark 1.3VS Engine MatchupThinking Machines: Inkling vs Meta: Muse Spark 1.1VS Engine MatchupThinking Machines: Inkling vs Z.ai: GLM 5 Turbo