Skip to main content
AI Choice Engine

Model comparison

Mistral Medium 3.5 vs NVIDIA Nemotron 3 Ultra

Mistral against NVIDIA, compared on context, price, and verified benchmark results.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Mistral

Mistral Medium 3.5

Frontier · Open weights

vs

NVIDIA

NVIDIA Nemotron 3 Ultra

Frontier · Open weights

AI model capability comparison
SpecificationMistral Medium 3.5NVIDIA Nemotron 3 Ultra
ProviderMistralNVIDIA
TierFrontierFrontier
Context window262KWinner: 1M
Max outputNot verifiedUnverifiedNot verifiedUnverified
Input / 1M tokens$1.50Winner: $0.50
Output / 1M tokens$7.50Winner: $2.20
WeightsOpenOpen
Parameters128B dense550B total / 55B active (MoE)
Reasoning levelsNot verifiedUnverifiedlow, high, max
Modalitiestext, imagetext
LicenseModified MITNot disclosedUnverified
API model idmistral-medium-3-5nemotron-3-ultra-550b-a55b
ReleasedApril 28, 2026June 4, 2026
Artificial Analysis Intelligence Index (2026-09-26)14.2Winner: 22.9

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

  • 2026-09-26
    Artificial Analysis

    Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.

    Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

Pricing tiers

Mistral Medium 3.5: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense.

NVIDIA Nemotron 3 Ultra: Open weights (weights + data + recipes); $0.50/$2.20 per MTok is the third-party hosted rate (OpenRouter; hosts report cached input $0.10, 262K served context and 16,384 output — secondary). 550B/55B MoE, 1M native context.

FrontierOpen weightsRecord checked September 26, 2026

Mistral Medium 3.5

Mistral Medium 3.5 is the model Mistral calls its new flagship — a 128B dense open-weight model with a 256K context, powering its Vibe remote agents.

Best for

  • EU-hosted frontier work
  • Open-weight self-hosting
  • Mistral Vibe agents

Watch out

Far behind US and Chinese frontier models on the Artificial Analysis index; max output is not published. Check the Modified MIT terms before redistribution.

FrontierOpen weightsRecord checked September 26, 2026

NVIDIA Nemotron 3 Ultra

Nemotron 3 Ultra is NVIDIA's open-weight (550B/55B) frontier MoE with a 1M-token context.

Best for

  • Open-weight frontier
  • Self-hosting on NVIDIA GPUs
  • Reasoning

Watch out

Top US open-weight until Thinking Machines Inkling; verify hosted pricing.

When the cheaper one wins

NVIDIA Nemotron 3 Ultra is cheaper on output at $2.20 per million tokens against $7.50 for Mistral Medium 3.5 — about 3.4×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 3/5 core specs verified on both sides — Not published for at least one side: max output, reasoning levels.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 2 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? Mistral Medium 3.5 · NVIDIA Nemotron 3 Ultra

Common questions

Mistral Medium 3.5 vs NVIDIA Nemotron 3 Ultra

Answered from the verified figures on this page rather than general guidance.

Is Mistral Medium 3.5 or NVIDIA Nemotron 3 Ultra cheaper for input?
NVIDIA Nemotron 3 Ultra is cheaper at $0.50 per million input tokens, against $1.50 for Mistral Medium 3.5 — roughly 3.0× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense. NVIDIA Nemotron 3 Ultra has tiered pricing: Open weights (weights + data + recipes); $0.50/$2.20 per MTok is the third-party hosted rate (OpenRouter; hosts report cached input $0.10, 262K served context and 16,384 output — secondary). 550B/55B MoE, 1M native context.
Is Mistral Medium 3.5 or NVIDIA Nemotron 3 Ultra cheaper for output?
NVIDIA Nemotron 3 Ultra is cheaper at $2.20 per million output tokens, against $7.50 for Mistral Medium 3.5 — roughly 3.4× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense. NVIDIA Nemotron 3 Ultra has tiered pricing: Open weights (weights + data + recipes); $0.50/$2.20 per MTok is the third-party hosted rate (OpenRouter; hosts report cached input $0.10, 262K served context and 16,384 output — secondary). 550B/55B MoE, 1M native context.
Which has the larger context window, Mistral Medium 3.5 or NVIDIA Nemotron 3 Ultra?
NVIDIA Nemotron 3 Ultra accepts 1M tokens against 262K for Mistral Medium 3.5. This only matters if you routinely send very long documents or large codebases.
Should I use Mistral Medium 3.5 or NVIDIA Nemotron 3 Ultra?
Both sit in the frontier tier, so the choice usually comes down to price and context rather than capability. Mistral Medium 3.5 suits eu-hosted frontier work; NVIDIA Nemotron 3 Ultra suits open-weight frontier.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: NVIDIA Nemotron 3 Ultra costs $0.50 per 1M tokens versus $1.50 for Mistral Medium 3.5 — a 3x difference at the headline tier.
  • Context: NVIDIA Nemotron 3 Ultra takes 1M against 262K for Mistral Medium 3.5 — only decisive if your prompts approach the smaller window.
  • Measured capability: NVIDIA Nemotron 3 Ultra leads Artificial Analysis Intelligence Index 22.9 to 14.2 (measured 2026-09-26).
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.