All Models
Inkling
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,...
Benchmarks
Available Providers (21)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | thinkingmachines/inkling | $0/MTok | $0/MTok | 1.0M | 16.4K | |
 Deep Infra | thinkingmachines/Inkling | $0.95/MTok | $4.05/MTok | 524.3K | 1.0M | |
 OpenRouter | thinkingmachines/inkling | $0.95/MTok | $4.05/MTok | 1.0M | 262.1K | |
 Eden AI | deepinfra/thinkingmachines/Inkling | $0.95/MTok | $4.05/MTok | 524.3K | 1.0M | |
 Kilo Gateway | thinkingmachines/inkling | $0.95/MTok | $4.05/MTok | 524.3K | 262.1K | |
 NanoGPT | thinkingmachines/inkling | $1/MTok | $4.05/MTok | 1.0M | 32.8K | |
 Hugging Face | thinkingmachines/Inkling | $1/MTok | $4.05/MTok | 1.0M | 1.0M | |
 Merge Gateway | thinkingmachines/inkling | $1/MTok | $4.05/MTok | 1.0M | 32K | |
 Together AI | thinkingmachines/Inkling | $1/MTok | $4.05/MTok | 524.3K | 131.1K | |
 Baseten | thinkingmachines/inkling | $1/MTok | $4.05/MTok | 1.0M | 32.8K | |
 Vercel AI Gateway | thinkingmachines/inkling | $1/MTok | $4.05/MTok | 256K | 256K | |
| Eden AI | together_ai/thinkingmachines/Inkling | $1/MTok | $4.05/MTok | 524.3K | 1.0M | |
 Fireworks AI | accounts/fireworks/models/inkling | $1/MTok | $4.05/MTok | 1.0M | 1.0M | |
 Modal | thinkingmachines/Inkling-NVFP4 | $1.20/MTok | $5/MTok | 1.0M | 262.1K | |
 Venice AI | inkling | $1.25/MTok | $5.06/MTok | 524.3K | 65.5K | |
 Requesty | inkling | $1.68/MTok | $4.21/MTok | 65.5K | 32.8K | |
 Impossibl | thinkingmachines/inkling | $1.87/MTok | $4.68/MTok | 65.5K | 65.5K | |
 LLMTR | thinkingmachines/inkling | $1.87/MTok | $4.68/MTok | 262.1K | 262.1K | |
 Thinking Machines | thinkingmachines/Inkling | $1.87/MTok | $4.68/MTok | 65.5K | 65.5K | |
 Abacus | thinkingmachines/Inkling | $3.74/MTok | $9.36/MTok | 262.1K | 131.1K | |
 Neon | inkling | —/MTok | —/MTok | 1.0M | 65.5K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output