NVIDIA H100 GPUs are here

📰 Replicate Blog

NVIDIA H100 GPUs are now available on Replicate, offering faster model training and deployment options

intermediate Published 16 May 2025
Action Steps
  1. Check the pricing for H100 GPUs on Replicate
  2. Create a new model using an H100 GPU via the web interface or HTTP API
  3. Explore the available hardware options, including 2x, 4x, and 8x configurations of A100s and L40S GPUs
Who Needs to Know This

Data scientists and machine learning engineers on a team can benefit from the increased computing power and flexibility of H100 GPUs for model training and deployment, while product managers can consider the cost implications and plan accordingly

Key Insight

💡 The availability of H100 GPUs on Replicate provides a significant boost to model training and deployment capabilities, with various configuration options to suit different needs and budgets

Share This
💡 NVIDIA H100 GPUs are now on Replicate! Faster model training and deployment options are here

Key Takeaways

NVIDIA H100 GPUs are now available on Replicate, offering faster model training and deployment options

Full Article

# NVIDIA H100 GPUs are here – Replicate blog

[Replicate has joined Cloudflare](https://replicate.com/blog/replicate-cloudflare)

[](https://replicate.com/)

cmd+k

[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)

Menu

[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)

* * *

[Compare models in the Playground](https://replicate.com/playground)

* Replicate
* [Blog](https://replicate.com/blog)

# NVIDIA H100 GPUs are here

Posted May 16, 2025 by
* [zeke](https://replicate.com/zeke)

You can now run NVIDIA H100 GPUs on Replicate.

You can also now use 2x, 4x, and 8x configurations of A100s and L40S GPUs. These were previously only available in [deployments](https://replicate.com/docs/topics/deployments), but now you can use them for regular models and training runs.

If you’ve been waiting to speed up your model or try something more powerful, now’s a good time.

## [](https://replicate.com/blog/nvidia-h100-gpus-are-here#h100-pricing)H100 pricing

1x H100s are now available to everyone.

2x, 4x, and 8x H100s are currently reserved for committed spend contracts.

Email us at [team@replicate.com](mailto:team@replicate.com) if you want access.

| Hardware | Price (per sec) | Price (per hour) | GPU | GPU RAM | CPU | RAM |
| --- | --- | --- | --- | --- | --- | --- |
| H100 | $0.001525 | $5.49 | 1x | 80GB | 13x | 72GB |
| 2x H100 | $0.003050 | $10.98 | 2x | 160GB | – | – |
| 4x H100 | $0.006100 | $21.96 | 4x | 320GB | – | – |
| 8x H100 | $0.012200 | $43.92 | 8x | 640GB | – | – |

## [](https://replicate.com/blog/nvidia-h100-gpus-are-here#a100-pricing-2x-4x-8x)A100 pricing (2x, 4x, 8x)

These multi-GPU setups for A100s are now available for models (they were already available for deployments):

| Hardware | Price (per sec) | Price (per hour) | GPU | GPU RAM | CPU | RAM |
| --- | --- | --- | --- | --- | --- | --- |
| 2x A100 (80GB) | $0.002800 | $10.08 | 2x | 160GB | 20x | 288GB |
| 4x A100 (80GB) | $0.005600 | $20.16 | 4x | 320GB | 40x | 576GB |
| 8x A100 (80GB) | $0.011200 | $40.32 | 8x | 640GB | 80x | 960GB |

See the [full hardware pricing list](https://replicate.com/pricing#hardware) for more details.

## [](https://replicate.com/blog/nvidia-h100-gpus-are-here#l40s-pricing-2x-4x-8x)L40S pricing (2x, 4x, 8x)

These multi-GPU setups for L40S GPUs are now available for models (they were already available for deployments):

| Hardware | Price (per sec) | Price (per hour) | GPU | GPU RAM | CPU | RAM |
| --- | --- | --- | --- | --- | --- | --- |
| 2x L40S | $0.001950 | $7.02 | 2x | 96GB | 20x | 144GB |
| 4x L40S | $0.003900 | $14.04 | 4x | 192GB | 40x | 288GB |
| 8x L40S | $0.007800 | $28.08 | 8x | 384GB | 80x | 576GB |

See the [full hardware pricing list](https://replicate.com/pricing#hardware) for more details.

## [](https://replicate.com/blog/nvidia-h100-gpus-are-here#creating-a-new-model-using-an-h100-gpu)Creating a new model using an H100 GPU

You can create a new model [on the web](https://replicate.com/create) or using the [HTTP API](https://replicate.com/docs/reference/http#models.create).

Here’s a cURL command to create a new model that uses an H100 GPU:

Copy

```
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H 'Content-Type: application/json' \
-d '{"owner": "my-username", "name": "my-model", "description": "An example model", "visibility": "private", "hardware": "gpu-h100"}' \
https://api.replicate.com/v1/models
```

## [](https://replicate.com/blog/nvidia-h100-gpus-are-here#listing-available-hardware-via-api)Listing available hardwar
Read full article → ← Back to Reads

Related Videos

Pole Pruner How A Rope Lever Shears High Branches
Pole Pruner How A Rope Lever Shears High Branches
Innoforge Studio
AI Mind Talks #4: Scaling Enterprise AI — with HiBob Head of AI Core Unit Yoni Friedman
AI Mind Talks #4: Scaling Enterprise AI — with HiBob Head of AI Core Unit Yoni Friedman
HiBob, modern HR made for modern business
MCP Security : Defense/ Guardrails
MCP Security : Defense/ Guardrails
Modern Security - Secuity Engineering Academy
103 Edge AI  On Device Intelligence
103 Edge AI On Device Intelligence
Sinsavk AI for beginners
Designing Machine Learning Systems | Chapter 7: Model Deployment & Prediction Service
Designing Machine Learning Systems | Chapter 7: Model Deployment & Prediction Service
onepagecode
LFM2.5-8B-A1B — Fastest Local AI Agent on a Laptop? (6 Tests)
LFM2.5-8B-A1B — Fastest Local AI Agent on a Laptop? (6 Tests)
Prompt Engineer