Model Terminal

Inkling Small

Inkling Small is a preview open-weights multimodal MoE model from Thinking Machines Lab with 276B total parameters and 12B active, accepting text, image, and audio inputs. It targets developers building chatbots, coding assistants, agentic pipelines, and RAG systems at lower latency and cost than its larger sibling Inkling. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Identity

Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed