Models/inkling

inklingActive · Cloud

OpenRouter · Released Jul 2026 · Apache-2.0

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,...

Context
1.0M
Max output
472K
Input
$1.00
Output
$4.05
Cached in
$0.17
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Details

ProviderOpenRouter
ReleasedJul 2026
LicenseApache-2.0
InputText
OutputText
Throughput-
Availability99.4%

Related models