See what this model actually costs to serve.

Fit is always evaluated when model sizing is available. GPU rent, paid idle capacity, API crossover, and measured optimization appear only when their required evidence exists. When the API wins, the page says so.

Model

black-forest-labs/FLUX.1-schnell

GPU

NVIDIA H100 SXM 80 GB

Requests/day

50,000

GPU count

1

Quantization

FP16

Tokens/request

500 in, 500 out

Charts appear only when evidence existsUtilization defaults to 30%

Configure the workload

Change the inputs, then calculate a shareable result.

Hugging Face model

GPUGPU countRequests per dayQuantizationAverage input tokensAverage output tokens

Fit confirmed

Cost needs a throughput source.

The fit verdict, compatible GPUs, and reproducing command are still useful. Money stays absent until this traffic shape has a complete measured, cited, or physics-bound evidence path.

Model

black-forest-labs/FLUX.1-schnell

Hardware

1 x NVIDIA H100 SXM 80 GB, FP16

Memory fit

Weights and KV cache stay separate so the fit is reproducible.

23.8 GB
Model weights: 0.7 GB
KV cache: 24.5 GB
Total required: 72 GB
Available

Provider price spread, NVIDIA H100 SXM 80 GB

Dated GPU-hour rental prices for this hardware. They are not monthly serving totals because throughput evidence is missing.

Scroll horizontally to read every chart label and value.

Source:

DigitalOcean, GPU Droplets, on demand, 1 day ago, captured 2026-08-08
Hyperstack, on demand, 1 day ago, captured 2026-08-08
Lambda Cloud, on demand, 1 day ago, captured 2026-08-08
Nebius, on demand, 1 day ago, captured 2026-08-08
RunPod, Community Cloud, on demand, 1 day ago, captured 2026-08-08
RunPod, Secure Cloud, on demand, 1 day ago, captured 2026-08-08
Verda, on demand, 1 day ago, captured 2026-08-08

What this chart means

These are GPU-hour rental prices only. A monthly serving total requires throughput evidence and remains absent.

Not measured on this config yet

No site-wide multiplier is applied. Run the exact configuration to create a receipt before comparing its measured baseline with RunInfra.

Run this configuration

Sources and caveats

Every published number keeps its source and date.

Provenance

Hugging Face model API revision sha
As of 2026-08-08
Hugging Face model API safetensors.total
As of 2026-08-08
Hugging Face config.json
As of 2026-08-08
NVIDIA H100 Tensor Core GPU datasheet
As of 2026-08-08
RunInfra Engine parameter-only KV-cache heuristic
As of 2026-08-08
NVIDIA L40S product specification
As of 2026-08-08
NVIDIA A100 product specification
As of 2026-08-08

Caveats

Workload class diffusion has no class-specific activation shape in CalcDataset. The kvCacheGb field is a parameter-based runtime-memory allowance used only for the VRAM budget. It is not an autoregressive KV-cache measurement, a backend compatibility test, or a serving performance estimate.
Class-specific activation dimensions are absent. Fit uses the configured input plus output token count only to scale its parameter-based runtime-memory allowance; that token shape is not presented as a workload-native request unit.
Workload class diffusion is not a decoder language model covered by this calculator. Memory fit remains available when model size is known, but output-token throughput, serving cost, the cost-vs-volume curve, API comparisons, the optimized delta, and a vLLM serve command are withheld because this workload's serving path and economic unit are not modelled here.
The Hugging Face repository is gated. Running the generated command requires authorized access to the model weights.

Fit confirmed

Cost needs a throughput source.

The fit verdict, compatible GPUs, and reproducing command are still useful. Money stays absent until this traffic shape has a complete measured, cited, or physics-bound evidence path.

Model

black-forest-labs/FLUX.1-schnell

Hardware

1 x NVIDIA H100 SXM 80 GB, FP16

Memory fit

Weights and KV cache stay separate so the fit is reproducible.

23.8 GB
Model weights: 0.7 GB
KV cache: 24.5 GB
Total required: 72 GB
Available

Provider price spread, NVIDIA H100 SXM 80 GB

Dated GPU-hour rental prices for this hardware. They are not monthly serving totals because throughput evidence is missing.

Scroll horizontally to read every chart label and value.

Source:

DigitalOcean, GPU Droplets, on demand, 1 day ago, captured 2026-08-08
Hyperstack, on demand, 1 day ago, captured 2026-08-08
Lambda Cloud, on demand, 1 day ago, captured 2026-08-08
Nebius, on demand, 1 day ago, captured 2026-08-08
RunPod, Community Cloud, on demand, 1 day ago, captured 2026-08-08
RunPod, Secure Cloud, on demand, 1 day ago, captured 2026-08-08
Verda, on demand, 1 day ago, captured 2026-08-08

What this chart means

These are GPU-hour rental prices only. A monthly serving total requires throughput evidence and remains absent.

Not measured on this config yet

No site-wide multiplier is applied. Run the exact configuration to create a receipt before comparing its measured baseline with RunInfra.

Run this configuration

Sources and caveats

Every published number keeps its source and date.

Provenance

Hugging Face model API revision sha
As of 2026-08-08
Hugging Face model API safetensors.total
As of 2026-08-08
Hugging Face config.json
As of 2026-08-08
NVIDIA H100 Tensor Core GPU datasheet
As of 2026-08-08
RunInfra Engine parameter-only KV-cache heuristic
As of 2026-08-08
NVIDIA L40S product specification
As of 2026-08-08
NVIDIA A100 product specification
As of 2026-08-08

Caveats

Workload class diffusion has no class-specific activation shape in CalcDataset. The kvCacheGb field is a parameter-based runtime-memory allowance used only for the VRAM budget. It is not an autoregressive KV-cache measurement, a backend compatibility test, or a serving performance estimate.
Class-specific activation dimensions are absent. Fit uses the configured input plus output token count only to scale its parameter-based runtime-memory allowance; that token shape is not presented as a workload-native request unit.
Workload class diffusion is not a decoder language model covered by this calculator. Memory fit remains available when model size is known, but output-token throughput, serving cost, the cost-vs-volume curve, API comparisons, the optimized delta, and a vLLM serve command are withheld because this workload's serving path and economic unit are not modelled here.
The Hugging Face repository is gated. Running the generated command requires authorized access to the model weights.

Fit confirmed

Cost needs a throughput source.

The fit verdict, compatible GPUs, and reproducing command are still useful. Money stays absent until this traffic shape has a complete measured, cited, or physics-bound evidence path.

Model

black-forest-labs/FLUX.1-schnell

Hardware

1 x NVIDIA H100 SXM 80 GB, FP16

Memory fit

Weights and KV cache stay separate so the fit is reproducible.

23.8 GB
Model weights: 0.7 GB
KV cache: 24.5 GB
Total required: 72 GB
Available

Provider price spread, NVIDIA H100 SXM 80 GB

Dated GPU-hour rental prices for this hardware. They are not monthly serving totals because throughput evidence is missing.

Scroll horizontally to read every chart label and value.

Source:

DigitalOcean, GPU Droplets, on demand, 1 day ago, captured 2026-08-08
Hyperstack, on demand, 1 day ago, captured 2026-08-08
Lambda Cloud, on demand, 1 day ago, captured 2026-08-08
Nebius, on demand, 1 day ago, captured 2026-08-08
RunPod, Community Cloud, on demand, 1 day ago, captured 2026-08-08
RunPod, Secure Cloud, on demand, 1 day ago, captured 2026-08-08
Verda, on demand, 1 day ago, captured 2026-08-08

What this chart means

These are GPU-hour rental prices only. A monthly serving total requires throughput evidence and remains absent.

Not measured on this config yet

No site-wide multiplier is applied. Run the exact configuration to create a receipt before comparing its measured baseline with RunInfra.

Run this configuration

Sources and caveats

Every published number keeps its source and date.

Provenance

Hugging Face model API revision sha
As of 2026-08-08
Hugging Face model API safetensors.total
As of 2026-08-08
Hugging Face config.json
As of 2026-08-08
NVIDIA H100 Tensor Core GPU datasheet
As of 2026-08-08
RunInfra Engine parameter-only KV-cache heuristic
As of 2026-08-08
NVIDIA L40S product specification
As of 2026-08-08
NVIDIA A100 product specification
As of 2026-08-08

Caveats

Workload class diffusion has no class-specific activation shape in CalcDataset. The kvCacheGb field is a parameter-based runtime-memory allowance used only for the VRAM budget. It is not an autoregressive KV-cache measurement, a backend compatibility test, or a serving performance estimate.
Class-specific activation dimensions are absent. Fit uses the configured input plus output token count only to scale its parameter-based runtime-memory allowance; that token shape is not presented as a workload-native request unit.
Workload class diffusion is not a decoder language model covered by this calculator. Memory fit remains available when model size is known, but output-token throughput, serving cost, the cost-vs-volume curve, API comparisons, the optimized delta, and a vLLM serve command are withheld because this workload's serving path and economic unit are not modelled here.
The Hugging Face repository is gated. Running the generated command requires authorized access to the model weights.

Fit confirmed

Cost needs a throughput source.

The fit verdict, compatible GPUs, and reproducing command are still useful. Money stays absent until this traffic shape has a complete measured, cited, or physics-bound evidence path.

Model

black-forest-labs/FLUX.1-schnell

Hardware

1 x NVIDIA H100 SXM 80 GB, FP16

Memory fit

Weights and KV cache stay separate so the fit is reproducible.

23.8 GB
Model weights: 0.7 GB
KV cache: 24.5 GB
Total required: 72 GB
Available

Provider price spread, NVIDIA H100 SXM 80 GB

Dated GPU-hour rental prices for this hardware. They are not monthly serving totals because throughput evidence is missing.

Scroll horizontally to read every chart label and value.

Source:

DigitalOcean, GPU Droplets, on demand, 1 day ago, captured 2026-08-08
Hyperstack, on demand, 1 day ago, captured 2026-08-08
Lambda Cloud, on demand, 1 day ago, captured 2026-08-08
Nebius, on demand, 1 day ago, captured 2026-08-08
RunPod, Community Cloud, on demand, 1 day ago, captured 2026-08-08
RunPod, Secure Cloud, on demand, 1 day ago, captured 2026-08-08
Verda, on demand, 1 day ago, captured 2026-08-08

What this chart means

These are GPU-hour rental prices only. A monthly serving total requires throughput evidence and remains absent.

Not measured on this config yet

No site-wide multiplier is applied. Run the exact configuration to create a receipt before comparing its measured baseline with RunInfra.

Run this configuration

Sources and caveats

Every published number keeps its source and date.

Provenance

Hugging Face model API revision sha
As of 2026-08-08
Hugging Face model API safetensors.total
As of 2026-08-08
Hugging Face config.json
As of 2026-08-08
NVIDIA H100 Tensor Core GPU datasheet
As of 2026-08-08
RunInfra Engine parameter-only KV-cache heuristic
As of 2026-08-08
NVIDIA L40S product specification
As of 2026-08-08
NVIDIA A100 product specification
As of 2026-08-08

Caveats

Workload class diffusion has no class-specific activation shape in CalcDataset. The kvCacheGb field is a parameter-based runtime-memory allowance used only for the VRAM budget. It is not an autoregressive KV-cache measurement, a backend compatibility test, or a serving performance estimate.
Class-specific activation dimensions are absent. Fit uses the configured input plus output token count only to scale its parameter-based runtime-memory allowance; that token shape is not presented as a workload-native request unit.
Workload class diffusion is not a decoder language model covered by this calculator. Memory fit remains available when model size is known, but output-token throughput, serving cost, the cost-vs-volume curve, API comparisons, the optimized delta, and a vLLM serve command are withheld because this workload's serving path and economic unit are not modelled here.
The Hugging Face repository is gated. Running the generated command requires authorized access to the model weights.

Share this calculation

Embed code appears only when the calculator can publish a sourced cost for a fitting configuration.

Badge unavailable for this configuration

The calculator does not have a complete throughput source for this workload, so it withheld the cost and does not generate embed code.

Turn this exact configuration into a deployment, describe what you need

End-to-end encryption

Isolated GPU infrastructure

No training on your data

SOC 2 Type II