ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Nemotron 3 Ultra 550B A55B vs Inkling Small

Inkling Small comes out ahead, 70 to 62 on our weighted score, and it is the cheaper option too.

  1. NVIDIA

    Nemotron 3 Ultra 550B A55B

    Released Jun 4, 2026

    62/100
    • ECI146.2
    • Price$0.50 / $2.50
    • Context1M
    Full specs Remove Nemotron 3 Ultra 550B A55B
  2. Our pick

    Thinking Machines

    Inkling Small

    Released Jul 30, 2026

    70/100
    • ECI150.2
    • Price$0.50 / $1.20
    • Context1.05M
    Full specs Remove Inkling Small

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Inkling Small is our pick

Inkling Small is the better all-round choice, scoring 70/100 against Nemotron 3 Ultra 550B A55B (62). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityInkling SmallCapabilities Index (ECI): Inkling Small 150.2 · Nemotron 3 Ultra 550B A55B 146.2
  • Lowest priceInkling SmallInkling Small $0.675 · Nemotron 3 Ultra 550B A55B $1.00 per 1M tokens (3:1 blend)
  • Longest contextInkling SmallInkling Small 1,048,576 · Nemotron 3 Ultra 550B A55B 1,000,000 tokens
  • Widest inputsInkling SmallNemotron 3 Ultra 550B A55B: Text · Inkling Small: Text, Images, Audio
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightNemotron 3 Ultra 550B A55BInkling Small
CapabilityCapabilities Index (ECI)50%7378
Price25%5058
Inputs & features15%4570
Context window10%6061
Overall100%62/10070/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Nemotron 3 Ultra 550B A55B vs Inkling Small specifications side by side
SpecificationNemotron 3 Ultra 550B A55BNVIDIAInkling SmallThinking Machines
Capability
Capabilities Index (ECI)146.2150.2 (best)
ECI rank#70 of 148#47 of 148 (best)
GPQA DiamondGraduate-level science questions85.4%88.5% (best)
FrontierMath Tiers 1–3Research-level mathematics—46.3%
OTIS Mock AIME 2024–2025Competition mathematics86.7%90.0% (best)
SimpleQA VerifiedShort factual questions—19.1%
Price per million tokens
Input$0.50$0.50
Output$2.50$1.20 (best)
Cached input$0.15—
Blended (3:1)$1.00$0.675 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Nvidia APIMedian of 11 providers
Limits
Context window1,000,000 tokens1,048,576 tokens (best)
Max output128,000 tokens1,048,576 tokens (best)
Inputs and features
TextYesYes
ImagesNoYes
PDFsNoNo
AudioNoYes
VideoNoNo
ReasoningYesYes
Tool callingYesYes
Structured outputYesNo
Availability
WeightsOpenOpenApache-2.0
API model IDnvidia/nemotron-3-ultra-550b-a55b—
API providers21 (best)11
ReleasedJun 4, 2026Jul 30, 2026
Knowledge cutoff——
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Nemotron 3 Ultra 550B A55B$10.00
  • Inkling Small$7.40
04 — Questions

Which should you choose?

Which is better: Nemotron 3 Ultra 550B A55B or Inkling Small?

Inkling Small is the better all-round choice, scoring 70/100 against Nemotron 3 Ultra 550B A55B (62). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Nemotron 3 Ultra 550B A55B or Inkling Small?

Inkling Small is cheaper at $0.50 input / $1.20 output per million tokens (median across 11 API providers). Nemotron 3 Ultra 550B A55B costs $0.50 input / $2.50 output per million tokens (official Nvidia API price). At a typical mix of three input tokens to one output token, that is $0.675 per million tokens for Inkling Small versus $1.00 for Nemotron 3 Ultra 550B A55B (1.5× as much).

Which scores higher on benchmarks?

Inkling Small scores higher on the Capabilities Index (ECI): Inkling Small 150.2 (#47 of 148) and Nemotron 3 Ultra 550B A55B 146.2 (#70 of 148). The confidence ranges of the top two overlap (147.5–152.1 vs 143.9–148.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Inkling Small 88.5%, Nemotron 3 Ultra 550B A55B 85.4%; OTIS Mock AIME 2024–2025 — Inkling Small 90.0%, Nemotron 3 Ultra 550B A55B 86.7%.

Which is better for coding?

There are no published SWE-bench Verified results for Nemotron 3 Ultra 550B A55B and Inkling Small yet, so there is no like-for-like coding score. On overall capability, Inkling Small leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Inkling Small has the largest context window at 1,048,576 tokens, against 1,000,000 for Nemotron 3 Ultra 550B A55B. Maximum output per response: Nemotron 3 Ultra 550B A55B up to 128,000, Inkling Small up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

Nemotron 3 Ultra 550B A55B accepts text; Inkling Small accepts text, images and audio. Inkling Small handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights (Apache-2.0), so you can self-host them.

Which is newer?

Inkling Small is the newest, released Jul 30, 2026. Nemotron 3 Ultra 550B A55B came out Jun 4, 2026.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons