Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 1M context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.
Beta
Modalities
In / out price
$2.3375 / $5.85
per 1M
Context
1M
Max output
66K
Released
Jul 16, 2026
Updated
Jul 17, 2026
Privacy
2 / 3Private routing
Private tier
- Anonymous
- Private
- E2EE
- Prompt and response content is not retained after the request.
- Request content is visible to the inference runtime while it is being processed.
Moderation
Not specified
No model-level moderation classification is recorded in this catalog.
Data retention
Zero retention
The provider reports that request content is discarded after inference.
Features
7Routing
2Anonrouter hosted
Routed through AnonRouter's gateway with metadata-only logging.
Provider direct
Requests egress directly to the provider runtime.
USD per 1M tokens from the Venice models API.