ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Llama 3.3 Nemotron Super 49B v1.5 vs Llama 3.1 Nemotron Ultra 253B vs GLM-4.5-Air

Llama 3.1 Nemotron Ultra 253B comes out ahead, 65 to 50 and 49 on our weighted score, and it is the cheaper option too.

  1. NVIDIA

    Llama 3.3 Nemotron Super 49B v1.5

    Released Jul 25, 2025Deprecated

    50/100
    • ECI—
    • Price$0.40 / $0.40
    • Context131K
    Full specs Remove Llama 3.3 Nemotron Super 49B v1.5
  2. Our pick

    NVIDIA

    Llama 3.1 Nemotron Ultra 253B

    Released Apr 7, 2025

    65/100
    • ECI—
    • PriceFree / Free
    • Context128K
    Full specs Remove Llama 3.1 Nemotron Ultra 253B

  3. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    49/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
    Full specs Remove GLM-4.5-Air
01 — Verdict

Llama 3.1 Nemotron Ultra 253B is our pick

Llama 3.1 Nemotron Ultra 253B is the better all-round choice, scoring 65/100 against Llama 3.3 Nemotron Super 49B v1.5 (50) and GLM-4.5-Air (49). It leads on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceLlama 3.1 Nemotron Ultra 253BLlama 3.1 Nemotron Ultra 253B Free · Llama 3.3 Nemotron Super 49B v1.5 $0.40 · GLM-4.5-Air $0.425 per 1M tokens (3:1 blend)
  • Longest contextLlama 3.3 Nemotron Super 49B v1.5 and GLM-4.5-AirLlama 3.3 Nemotron Super 49B v1.5 131,072 · GLM-4.5-Air 131,072 · Llama 3.1 Nemotron Ultra 253B 128,000 tokens
  • Widest inputsSame inputsLlama 3.3 Nemotron Super 49B v1.5: Text · Llama 3.1 Nemotron Ultra 253B: Text · GLM-4.5-Air: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama 3.3 Nemotron Super 49B v1.5Llama 3.1 Nemotron Ultra 253BGLM-4.5-Air
Price50%6910068
Inputs & features30%353535
Context window20%242424
Overall100%50/10065/10049/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Llama 3.3 Nemotron Super 49B v1.5 vs Llama 3.1 Nemotron Ultra 253B vs GLM-4.5-Air specifications side by side
SpecificationLlama 3.3 Nemotron Super 49B v1.5NVIDIALlama 3.1 Nemotron Ultra 253BNVIDIAGLM-4.5-AirZ.ai (Zhipu)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.40Free (best)$0.20
Output$0.40Free (best)$1.10
Cached input——$0.03
Blended (3:1)$0.40Free (best)$0.425
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Nvidia APIOfficial Z.AI API
Limits
Context window131,072 tokens (best)128,000 tokens131,072 tokens (best)
Max output131,072 tokens (best)8,192 tokens98,304 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model IDnvidia/llama-3.3-nemotron-super-49b-v1.5nvidia/llama-3.1-nemotron-ultra-253b-v1glm-4.5-air
API providers2113 (best)
ReleasedJul 25, 2025Apr 7, 2025Jul 28, 2025
Knowledge cutoff——Apr 2025
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.

  • Llama 3.3 Nemotron Super 49B v1.5$4.80
  • Llama 3.1 Nemotron Ultra 253BFree
  • GLM-4.5-Air$4.20
04 — Questions

Which should you choose?

Which is better: Llama 3.3 Nemotron Super 49B v1.5, Llama 3.1 Nemotron Ultra 253B or GLM-4.5-Air?

Llama 3.1 Nemotron Ultra 253B is the better all-round choice, scoring 65/100 against Llama 3.3 Nemotron Super 49B v1.5 (50) and GLM-4.5-Air (49). It leads on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Llama 3.3 Nemotron Super 49B v1.5, Llama 3.1 Nemotron Ultra 253B or GLM-4.5-Air?

Llama 3.1 Nemotron Ultra 253B is cheaper at Free input / Free output per million tokens (official Nvidia API price). Llama 3.3 Nemotron Super 49B v1.5 costs $0.40 input / $0.40 output per million tokens (median across 1 API provider; free on Nvidia); GLM-4.5-Air costs $0.20 input / $1.10 output per million tokens (official Z.AI API price). Llama 3.1 Nemotron Ultra 253B is listed as free.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Llama 3.3 Nemotron Super 49B v1.5 has not been scored yet, Llama 3.1 Nemotron Ultra 253B has not been scored yet and GLM-4.5-Air has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Llama 3.3 Nemotron Super 49B v1.5, Llama 3.1 Nemotron Ultra 253B and GLM-4.5-Air yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Llama 3.3 Nemotron Super 49B v1.5 and GLM-4.5-Air have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Llama 3.1 Nemotron Ultra 253B. Maximum output per response: Llama 3.3 Nemotron Super 49B v1.5 up to 131,072, Llama 3.1 Nemotron Ultra 253B up to 8,192, GLM-4.5-Air up to 98,304 tokens.

Which can read images, PDFs, audio or video?

Llama 3.3 Nemotron Super 49B v1.5 accepts text; Llama 3.1 Nemotron Ultra 253B accepts text; GLM-4.5-Air accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

GLM-4.5-Air is the newest, released Jul 28, 2025. Llama 3.3 Nemotron Super 49B v1.5 came out Jul 25, 2025; Llama 3.1 Nemotron Ultra 253B came out Apr 7, 2025. Knowledge cutoff: GLM-4.5-Air Apr 2025.

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