Back to Models Directory
Thinkingmachinesinkling-2-mini

Thinking Machines: Inkling 2 Mini API Pricing

Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...

Base Input Price$0.075/ 1M tokens
Base Output Price$0.30/ 1M tokens
Prompt Cache Read$0.015-80% discount
Batch API RateN/A24h async offload

Recommended Coding Agents & Harnesses

Compare all 7 harnesses →
AiderCLI
BaseURL
Multiplier1.2x – 1.8x
Cache Match~84% Hit
Setup Config →
OpenCode / ContinuePlugin
BaseURL
Multiplier1.5x – 2.3x
Cache Match~79% Hit
Setup Config →
Roo CodePlugin
BaseURL
Multiplier1.7x – 2.6x
Cache Match~84% Hit
Setup Config →

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
Thinkingmachines Direct$0.075$0.30SupportedConnect
OpenRouter$0.075$0.30SupportedConnect