---
title: "Nemotron 3 Ultra vs Mistral Large 3 API pricing compared"
description: "Nemotron 3 Ultra vs Mistral Large 3 API price per 1M tokens: USD 0.50 / USD 2.15 vs USD 0.50 / USD 1.50 input/output, from providers' own pricing pages."
url: https://broadrouter.com/llm-api-pricing/compare/nemotron-3-ultra-550b-a55b-vs-mistral-large-2512/
lang: en
updated: 2026-11-16
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Nemotron 3 Ultra vs Mistral Large 3 API pricing

Updated 2026-11-16

Nemotron 3 Ultra: USD 0.50 input, USD 2.15 output per 1M tokens (CoreWeave Forge). Mistral Large 3: USD 0.50 input, USD 1.50 output per 1M tokens (Amazon Bedrock). At 3 input tokens per output token, Nemotron 3 Ultra costs 22% more than Mistral Large 3 (USD 0.9125 vs USD 0.75 per 1M).

Picked by the same-tier rule: both are in the third quarter of the indexed models by price (USD 0.4512 to USD 1.40 per 1M tokens at 3:1) and in the same size class, large (a tier word such as Pro, Opus or Max, or 200B parameters or more). Nemotron 3 Ultra is the 2nd-closest-priced model from another maker to Mistral Large 3 in that bucket. **Price only**: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-16), with no claim about quality, speed or accuracy.

## How do Nemotron 3 Ultra and Mistral Large 3 differ on price?

-   Cheapest input price: both USD 0.50 per 1M tokens.
-   Cheapest output price: Mistral Large 3 USD 1.50 against USD 2.15 per 1M tokens, so Nemotron 3 Ultra costs 1.43× as much (43% more).
-   Among the 201 indexed models, Nemotron 3 Ultra ranks 128th cheapest and Mistral Large 3 118th on the 3:1 blend.
-   No input:output mix changes the answer: Mistral Large 3 is cheaper at every mix before cache discounts.
-   Only Nemotron 3 Ultra lists a cached-input discount: Nemotron 3 Ultra at 10 standard prices of 10, from USD 0.10 (CoreWeave Forge, 80% below that provider's input price). Mistral Large 3's cached tokens bill at the input price.
-   Only Nemotron 3 Ultra has a stated context window (262,144 tokens); no provider of Mistral Large 3 states one on its pricing page.
-   Nemotron 3 Ultra has 10 providers with a standard price, 7 more than Mistral Large 3; no provider sells both, so using both means two accounts.
-   Shopping around matters more for Mistral Large 3: its dearest standard price is 1.83× its cheapest, against 1.37× for Nemotron 3 Ultra.
-   Nemotron 3 Ultra has a batch price at 1 provider, from USD 0.4625 at 3:1 (Doubleword); Mistral Large 3 has no batch price on file.
-   For the one-developer coding agent preset, the gap is USD 6,642 a year in Nemotron 3 Ultra's favour (Nemotron 3 Ultra USD 481.50 a month, Mistral Large 3 USD 1,035).

## Nemotron 3 Ultra and Mistral Large 3 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Nemotron 3 Ultra and Mistral Large 3 API prices compared
| Price | Nemotron 3 Ultra | Mistral Large 3 |
| --- | --- | --- |
| Model page | [NVIDIA Nemotron 3 Ultra](https://broadrouter.com/llm-api-pricing/nemotron-3-ultra-550b-a55b/) · NVIDIA · 10 providers | [Mistral Large 3](https://broadrouter.com/llm-api-pricing/mistral-large-2512/) · Mistral AI · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.9125 · USD 0.50 in / USD 2.15 out at CoreWeave Forge · [CoreWeave Forge page](https://coreweave.com/forge-pricing/inference-agents) checked 2026-11-15 | USD 0.75 lower · USD 0.50 in / USD 1.50 out at Amazon Bedrock · [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) checked 2026-11-14 |
| Cheapest input | USD 0.50 tie · CoreWeave Forge [source](https://coreweave.com/forge-pricing/inference-agents) | USD 0.50 tie · Amazon Bedrock [source](https://aws.amazon.com/bedrock/pricing/) |
| Cheapest cached input | USD 0.10 · CoreWeave Forge [source](https://coreweave.com/forge-pricing/inference-agents) | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 2.15 · CoreWeave Forge [source](https://coreweave.com/forge-pricing/inference-agents) | USD 1.50 lower · Amazon Bedrock [source](https://aws.amazon.com/bedrock/pricing/) |
| Maker's own API | NVIDIA publishes no paid standard price on its own API that we found. | Mistral AI publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.55 / USD 2.40 · input / output, 10 prices | USD 0.636 / USD 1.908 · input / output, 3 prices |
| Context window | 262,144 tokens, largest stated; from 256,000 at some providers | No provider states one on its pricing page. |
| Providers with a standard price | 10 | 3 |

-   **Lower** marks the lower price on a line; **tie**, equal prices. Other tiers and free rows are on the model pages.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Nemotron%203%20Ultra%20vs%20Mistral%20Large%203%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fcompare%2Fnemotron-3-ultra-550b-a55b-vs-mistral-large-2512%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What do Nemotron 3 Ultra and Mistral Large 3 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the [cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=nemotron-3-ultra-550b-a55b,mistral-large-2512); cached input at the cached price where listed).

Monthly cost of three workloads on Nemotron 3 Ultra and Mistral Large 3
| Workload | Nemotron 3 Ultra | Mistral Large 3 | Difference |
| --- | --- | --- | --- |
| **Support chatbot** · 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 62.10 · CoreWeave Forge | USD 72.00 · Amazon Bedrock | USD 9.90 · Nemotron 3 Ultra lower |
| **RAG over documents** · 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 123.45 · CoreWeave Forge | USD 142.50 · Amazon Bedrock | USD 19.05 · Nemotron 3 Ultra lower |
| **Coding agent (one developer)** · 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 481.50 · CoreWeave Forge | USD 1,035 · Amazon Bedrock | USD 553.50 · Nemotron 3 Ultra lower |

Nemotron 3 Ultra is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.15× as much as the cheaper one.

## Does the cheaper model change with your input:output ratio?

Mistral Large 3 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Nemotron 3 Ultra's, so the input:output ratio never changes the answer. On input price alone they tie.

Price per 1M tokens of Nemotron 3 Ultra and Mistral Large 3 at different input:output mixes
| Input : output tokens | Nemotron 3 Ultra | Mistral Large 3 |
| --- | --- | --- |
| **1 : 3** (long answers) | USD 1.737 · CoreWeave Forge | USD 1.25 lower · Amazon Bedrock |
| **1 : 1** | USD 1.325 · CoreWeave Forge | USD 1 lower · Amazon Bedrock |
| **3 : 1** (the site’s blend) | USD 0.9125 · CoreWeave Forge | USD 0.75 lower · Amazon Bedrock |
| **10 : 1** (retrieval, long prompts) | USD 0.65 · CoreWeave Forge | USD 0.5909 lower · Amazon Bedrock |
| **30 : 1** (agents, big contexts) | USD 0.5532 · CoreWeave Forge | USD 0.5323 lower · Amazon Bedrock |

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

## What do Nemotron 3 Ultra and Mistral Large 3 cost per character in other languages?

Not measured: the [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/) covers only tokenizers we could measure from published files, and Mistral Large 3 is not among them. Count tokens on your own text with the counters below.

## Check it on your own traffic

-   [NVIDIA Nemotron 3 Ultra API pricing](https://broadrouter.com/llm-api-pricing/nemotron-3-ultra-550b-a55b/): all 10 providers and other tiers.
-   [Mistral Large 3 API pricing](https://broadrouter.com/llm-api-pricing/mistral-large-2512/): all 3 providers and other tiers.
-   [Cost calculator with Nemotron 3 Ultra and Mistral Large 3 preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=nemotron-3-ultra-550b-a55b,mistral-large-2512)
-   [Nemotron 3 token counter](https://broadrouter.com/tools/nemotron-token-counter/)
-   [Token counter](https://broadrouter.com/tools/token-counter/)
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/)

More comparisons: [GLM 5.3 vs Nemotron 3 Ultra](https://broadrouter.com/llm-api-pricing/compare/glm-5.3-vs-nemotron-3-ultra-550b-a55b/) · [every Nemotron 3 Ultra comparison](https://broadrouter.com/llm-api-pricing/compare/#m-nemotron-3-ultra-550b-a55b) · [every Mistral Large 3 comparison](https://broadrouter.com/llm-api-pricing/compare/#m-mistral-large-2512) · [all 662 price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

## Questions

### Is Nemotron 3 Ultra cheaper than Mistral Large 3?

No. On a blend of 3 input tokens to 1 output token, Mistral Large 3 costs USD 0.75 per 1M tokens and Nemotron 3 Ultra USD 0.9125, at each model's cheapest standard price. For input alone, both start at USD 0.50 per 1M; for output alone, Mistral Large 3 is (USD 1.50 against USD 2.15). This compares price only, not quality.

### What do Nemotron 3 Ultra and Mistral Large 3 cost per 1M tokens?

Nemotron 3 Ultra: from USD 0.50 input and USD 2.15 output at CoreWeave Forge; median of 10 standard prices USD 0.55 / USD 2.40. Mistral Large 3: from USD 0.50 input and USD 1.50 output at Amazon Bedrock; median of 3 standard prices USD 0.636 / USD 1.908. Each price is read from the provider's own pricing page; the source is linked in the table.

### Which providers sell both Nemotron 3 Ultra and Mistral Large 3?

None of the providers we track sells both at a standard price. Nemotron 3 Ultra is cheapest at CoreWeave Forge and Mistral Large 3 at Amazon Bedrock, so running both means two accounts.

### Which is cheaper for a coding agent or a chatbot, Nemotron 3 Ultra or Mistral Large 3?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 481.50 a month on Nemotron 3 Ultra (CoreWeave Forge) against USD 1,035 on Mistral Large 3 (Amazon Bedrock), a difference of USD 553.50. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 62.10 a month on Nemotron 3 Ultra (CoreWeave Forge) against USD 72.00 on Mistral Large 3 (Amazon Bedrock), a difference of USD 9.90. Each uses the cheapest standard price for that workload, cached input included. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=nemotron-3-ultra-550b-a55b,mistral-large-2512).

### At what input:output ratio does the cheaper of Nemotron 3 Ultra and Mistral Large 3 change?

Mistral Large 3 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Nemotron 3 Ultra's, so the input:output ratio never changes the answer. On input price alone they tie.

### Do Nemotron 3 Ultra and Mistral Large 3 have cached input pricing?

Nemotron 3 Ultra from USD 0.10 per 1M cached input tokens (CoreWeave Forge; 10 of 10 standard prices list a discount). Mistral Large 3: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-compare-nemotron-3-ultra-550b-a55b-vs-mistral-large-2512&utm_content=page-cta) ·

**Sources**

-   [CoreWeave Forge: pricing (checked 2026-11-15)](https://coreweave.com/forge-pricing/inference-agents)
-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [Doubleword: pricing (checked 2026-11-16)](https://docs.doubleword.ai/inference-api/models)
