Model comparison
Compare Inkling and NVIDIA Nemotron 3 Ultra using the same provider-sourced text & reasoning rubric. No mystery score and no invented benchmark ranking.
Facts checked September 4, 2026
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
| Model | Access | Estimated total (USD) |
|---|---|---|
| InklingThinking Machines Lab | Thinking Machines Lab | No reviewed rate |
| NVIDIA Nemotron 3 UltraNVIDIA | NVIDIA | No reviewed rate |
Quick take
Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.
A 975B model is a serious serving project even with sparse activation. Compare the exact hosted or self-hosted route, and do not assume the model's 1M maximum context is available on every provider.
NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.
Self-hosting Ultra is a substantial hardware project. Size the real context cache, concurrency, precision, and availability requirements before treating open weights as the cheaper route.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Text & reasoning | Inkling | NVIDIA Nemotron 3 Ultra |
|---|---|---|
| Context windowMaximum combined prompt and working context documented by the provider. | Up to 1M tokens; Tinker offers 64K and 256K | Up to 1M tokens |
| Maximum outputProvider-published response limit, where available. | Not separately published | Not separately published |
| Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff. | Not published | Pretraining through Sep 2025; post-training through May 2026 |
| Input priceCurrent standard list price per million input tokens unless noted. | Hosting dependent | Free prototype or deployment cost |
| Output priceCurrent standard list price per million output tokens unless noted. | Hosting dependent | Free prototype or deployment cost |
| InputsMedia types accepted by the listed model endpoint. | Text, image, audio | Text |
| Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list. | Agentic coding, tools, Python-assisted vision, controllable thinking | Tool calling, agents, configurable reasoning budget |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
The open weights can be self-hosted so request data stays in infrastructure you control. Tinker and partner-hosted routes have separate retention and training-use terms that must be checked with the selected provider.
Downloaded weights can run in infrastructure the operator controls. NVIDIA's hosted prototype and partner endpoints are governed by their own trial, logging, retention, and deployment terms.
Provider and API links
Frequently asked questions
Inkling: Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows. NVIDIA Nemotron 3 Ultra: NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.
Consider Inkling when your priority is Teams that want an adaptable open-weight foundation model. Consider NVIDIA Nemotron 3 Ultra when your priority is Complex long-running agents. Test both with your own data and provider route before committing.
No. This comparison aligns provider-published facts for the Text & reasoning category. It does not claim a universal winner or combine incompatible third-party benchmark scores.
