Thinking Machines: Inkling Small
THINKINGMACHINES Developer Architecture Profile
Intelligence (ELO)1427Chatbot Arena Verified
Max Context Limit524,288Max Out: 262,144 tokens
Prompt Caching78% OFF$0.10 / 1M cached
Standard API / 1M$1.65🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Audio Gen
- Reasoning
- Coding & Logic
- Fictional
- 🧠 Extended Test-Time Reasoning
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.45 / 1M
⚡ Cached Input (Prompt Cache Read)78% OFF$0.10 / 1M
Output Tokens (Completion)$1.20 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupThinking Machines: Inkling Small vs SpaceXAI: Grok 4.3 (batch)VS Engine MatchupThinking Machines: Inkling Small vs DeepSeek: DeepSeek V3.2VS Engine MatchupThinking Machines: Inkling Small vs DeepSeek: R1 0528VS Engine MatchupThinking Machines: Inkling Small vs OpenAI: o4 MiniVS Engine MatchupThinking Machines: Inkling Small vs Cohere: Command A+VS Engine MatchupThinking Machines: Inkling Small vs DeepSeek: DeepSeek V4.1 Flash