ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Apertus 8B vs Nemotron Nano 9B v2 vs Voxtral Small 24B 2507

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Swiss AI

    Apertus 8B

    Released Sep 2, 2025

    56/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
  2. NVIDIA

    Nemotron Nano 9B v2

    Released Aug 18, 2025

    63/100
    • ECI—
    • Price$0.06 / $0.23
    • Context131K
  3. Mistral AI

    Voxtral Small 24B 2507

    Released Jul 15, 2025

    57/100
    • ECI—
    • Price$0.10 / $0.40
    • Context33K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Nemotron Nano 9B v2 63/100, Voxtral Small 24B 2507 57/100, Apertus 8B 56/100) compare the available specifications and 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 priceNemotron Nano 9B v2Nemotron Nano 9B v2 $0.102 · Apertus 8B $0.125 · Voxtral Small 24B 2507 $0.175 per 1M tokens (3:1 blend)
  • Longest contextNemotron Nano 9B v2Nemotron Nano 9B v2 131,072 · Apertus 8B 65,536 · Voxtral Small 24B 2507 32,768 tokens
  • Widest inputsVoxtral Small 24B 2507Apertus 8B: Text · Nemotron Nano 9B v2: Text · Voxtral Small 24B 2507: Text, Audio
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightApertus 8BNemotron Nano 9B v2Voxtral Small 24B 2507
Price50%899382
Inputs & features30%253545
Context window20%223211
Specs & price only100%56/10063/10057/100

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.

Apertus 8B vs Nemotron Nano 9B v2 vs Voxtral Small 24B 2507 specifications side by side
SpecificationApertus 8BSwiss AINemotron Nano 9B v2NVIDIAVoxtral Small 24B 2507Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.10$0.06 (best)$0.10
Output$0.20 (best)$0.23$0.40
Cached input———
Blended (3:1)$0.125$0.102 (best)$0.175
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 4 providersOfficial Mistral API
Limits
Context window65,536 tokens131,072 tokens (best)32,768 tokens
Max output8,192 tokens131,072 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoYes
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenApache-2.0OpenOpenApache 2.0
API model ID——voxtral-small-latest
API providers149 (best)
ReleasedSep 2, 2025Aug 18, 2025Jul 15, 2025
Knowledge cutoffSep 2025Sep 2024—
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.

  • Apertus 8B$1.40
  • Nemotron Nano 9B v2$1.06
  • Voxtral Small 24B 2507$1.80
04 — Questions

Which should you choose?

Which is better: Apertus 8B, Nemotron Nano 9B v2 or Voxtral Small 24B 2507?

There is not enough shared capability evidence to name an overall winner. The scores (Nemotron Nano 9B v2 63/100, Voxtral Small 24B 2507 57/100, Apertus 8B 56/100) compare the available specifications and 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, Apertus 8B, Nemotron Nano 9B v2 or Voxtral Small 24B 2507?

Nemotron Nano 9B v2 is cheaper at $0.06 input / $0.23 output per million tokens (median across 4 API providers). Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider); Voxtral Small 24B 2507 costs $0.10 input / $0.40 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.102 per million tokens for Nemotron Nano 9B v2 versus $0.125 for Apertus 8B (1.2× as much) and $0.175 for Voxtral Small 24B 2507 (1.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Nemotron Nano 9B v2 has not been scored yet and Voxtral Small 24B 2507 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Apertus 8B, Nemotron Nano 9B v2 and Voxtral Small 24B 2507 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?

Nemotron Nano 9B v2 has the largest context window at 131,072 tokens, against 65,536 for Apertus 8B and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Apertus 8B up to 8,192, Nemotron Nano 9B v2 up to 131,072, Voxtral Small 24B 2507 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Apertus 8B accepts text; Nemotron Nano 9B v2 accepts text; Voxtral Small 24B 2507 accepts text and audio. Voxtral Small 24B 2507 handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

Apertus 8B is the newest, released Sep 2, 2025. Nemotron Nano 9B v2 came out Aug 18, 2025; Voxtral Small 24B 2507 came out Jul 15, 2025. Knowledge cutoff: Apertus 8B Sep 2025, Nemotron Nano 9B v2 Sep 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 Nov 18, 2026.