Thinking Machines: Inkling (batch)thinkingmachines
Thinking Machines: Inkling (batch): $1.00/1M input, $4.05/1M output, 524K context. 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,...
API Pricing (per 1M tokens)
| Input | $1.00 |
| Output | $4.05 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.76 |
Specs & Performance
| Context Length | 524K |
| Max Output | 472K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, image, audio → text |
More from thinkingmachines
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Thinking Machines: Inkling (batch) API cost?
Thinking Machines: Inkling (batch) costs $1.00/1M input tokens and $4.05/1M output tokens. Blended cost at a 3:1 ratio is about $1.76/1M tokens.
What is the context window of Thinking Machines: Inkling (batch)?
Thinking Machines: Inkling (batch) supports a 524K token context window with up to 472K output tokens.
Is Thinking Machines: Inkling (batch) worth it?
Thinking Machines: Inkling (batch) has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.