You only pay for what you use on Replicate, billed by the second. When you don't run anything, it scales to zero and you don't pay a thing.
Hardware | Price | GPU | CPU | GPU RAM | RAM |
---|---|---|---|---|---|
CPU cpu | $0.000100/sec $0.36/hr | - | 4x | - | 8GB |
Nvidia A100 (80GB) GPU gpu-a100-large | $0.001400/sec $5.04/hr | 1x | 10x | 80GB | 144GB |
2x Nvidia A100 (80GB) GPU gpu-a100-large-2x | $0.002800/sec $10.08/hr | 2x | 20x | 160GB | 288GB |
4x Nvidia A100 (80GB) GPU gpu-a100-large-4x | $0.005600/sec $20.16/hr | 4x | 40x | 320GB | 576GB |
8x Nvidia A100 (80GB) GPU gpu-a100-large-8x | $0.011200/sec $40.32/hr | 8x | 80x | 640GB | 960GB |
Nvidia L40S GPU gpu-l40s | $0.000975/sec $3.51/hr | 1x | 10x | 48GB | 65GB |
2x Nvidia L40S GPU gpu-l40s-2x | $0.001950/sec $7.02/hr | 2x | 20x | 96GB | 144GB |
4x Nvidia L40S GPU gpu-l40s-4x | $0.003900/sec $14.04/hr | 4x | 40x | 192GB | 288GB |
8x Nvidia L40S GPU gpu-l40s-8x | $0.007800/sec $28.08/hr | 8x | 80x | 384GB | 576GB |
Nvidia T4 GPU gpu-t4 | $0.000225/sec $0.81/hr | 1x | 4x | 16GB | 16GB |
Additional hardware | |||||
Nvidia H100 GPU gpu-h100 | $0.001525/sec $5.49/hr | Flux fine-tunes run on H100s; additional H100 capacity is reserved for committed spend contracts. | |||
2x Nvidia H100 GPU gpu-h100-2x | $0.003050/sec $10.98/hr | Flux fine-tunes run on H100s; additional H100 capacity is reserved for committed spend contracts. | |||
4x Nvidia H100 GPU gpu-h100-4x | $0.006100/sec $21.96/hr | Flux fine-tunes run on H100s; additional H100 capacity is reserved for committed spend contracts. | |||
8x Nvidia H100 GPU gpu-h100-8x | $0.012200/sec $43.92/hr | Flux fine-tunes run on H100s; additional H100 capacity is reserved for committed spend contracts. |
Thousands of open-source machine learning models have been contributed by our community and more are added every day. When running or training one of these models, you only pay for time it takes to process your request.
Each model runs on different hardware and takes a different amount of time to run. You'll find estimates for how much they cost under "Run time and cost" on the model's page. For example, for stability-ai/sdxl:
This model costs approximately $0.0036 to run on Replicate, or 277 runs per $1, but this varies depending on your inputs.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 4 seconds.
Replicate hosts some audio models that are either priced per audio file, or per second of audio generated by the model.
Model | Output |
---|---|
minimax/music-01 | $0.035 / audio-file |
Model | Output |
---|---|
playht/play-dialog | $0.001 / second of audio |
Replicate hosts some video models that are either priced per video, or per second of video generated by the model.
Model | Output |
---|---|
luma/ray | $0.45 / video |
minimax/video-01 | $0.50 / video |
minimax/video-01-director | $0.50 / video |
minimax/video-01-live | $0.50 / video |
Model | Output |
---|---|
google/veo-2 | $0.500 / second of video |
haiper-ai/haiper-video-2 | $0.050 / second of video |
kwaivgi/kling-v1.6-pro | $0.098 / second of video |
kwaivgi/kling-v1.6-standard | $0.056 / second of video |
kwaivgi/kling-v2.0 | $0.280 / second of video |
luma/ray-2-540p | $0.100 / second of video |
luma/ray-2-720p | $0.180 / second of video |
luma/ray-flash-2-540p | $0.033 / second of video |
luma/ray-flash-2-720p | $0.060 / second of video |
topazlabs/video-upscale | $0.100 / second of video |
wavespeedai/hunyuan-video-fast | $0.200 / second of video |
wavespeedai/wan-2.1-i2v-480p | $0.090 / second of video |
wavespeedai/wan-2.1-i2v-720p | $0.250 / second of video |
wavespeedai/wan-2.1-t2v-480p | $0.070 / second of video |
wavespeedai/wan-2.1-t2v-720p | $0.240 / second of video |
Replicate hosts some training models that are priced per training step.
Model | Input |
---|---|
black-forest-labs/flux-pro-trainer | $0.014 / training step |
Replicate hosts some language models that are priced per token.
Model | Input | Output |
---|---|---|
anthropic/claude-3.5-haiku | $1.00 / 1M tokens | $5.00 / 1M tokens |
anthropic/claude-3.5-sonnet | $3.75 / 1M tokens | $18.75 / 1M tokens |
anthropic/claude-3.7-sonnet | $3.00 / 1M tokens | $15.00 / 1M tokens |
deepseek-ai/deepseek-r1 | $3.75 / 1M tokens | $10.00 / 1M tokens |
deepseek-ai/deepseek-v3 | $1.45 / 1M tokens | $1.45 / 1M tokens |
ibm-granite/granite-20b-code-instruct-8k | $0.10 / 1M tokens | $0.50 / 1M tokens |
ibm-granite/granite-3.0-2b-instruct | $0.03 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-3.0-8b-instruct | $0.05 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-3.1-2b-instruct | $0.03 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-3.1-8b-instruct | $0.03 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-3.2-8b-instruct | $0.03 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-3.3-8b-instruct | $0.03 / 1M tokens | $0.25 / 1M tokens |
ibm-granite/granite-8b-code-instruct-128k | $0.05 / 1M tokens | $0.25 / 1M tokens |
meta/llama-2-13b | $0.10 / 1M tokens | $0.50 / 1M tokens |
meta/llama-2-13b-chat | $0.10 / 1M tokens | $0.50 / 1M tokens |
meta/llama-2-70b | $0.65 / 1M tokens | $2.75 / 1M tokens |
meta/llama-2-70b-chat | $0.65 / 1M tokens | $2.75 / 1M tokens |
meta/llama-2-7b | $0.05 / 1M tokens | $0.25 / 1M tokens |
meta/llama-2-7b-chat | $0.05 / 1M tokens | $0.25 / 1M tokens |
meta/llama-4-maverick-instruct | $0.25 / 1M tokens | $0.95 / 1M tokens |
meta/llama-4-scout-instruct | $0.17 / 1M tokens | $0.65 / 1M tokens |
meta/meta-llama-3.1-405b-instruct | $9.50 / 1M tokens | $9.50 / 1M tokens |
meta/meta-llama-3-70b | $0.65 / 1M tokens | $2.75 / 1M tokens |
meta/meta-llama-3-70b-instruct | $0.65 / 1M tokens | $2.75 / 1M tokens |
meta/meta-llama-3-8b | $0.05 / 1M tokens | $0.25 / 1M tokens |
meta/meta-llama-3-8b-instruct | $0.05 / 1M tokens | $0.25 / 1M tokens |
mistralai/mistral-7b-v0.1 | $0.05 / 1M tokens | $0.25 / 1M tokens |
You aren't limited to the public models on Replicate: you can deploy your own custom models using Cog, our open-source tool for packaging machine learning models.
Unlike public models, most private models (with the exception of fast booting models) run on dedicated hardware so you don't have to share a queue with anyone else. This means you pay for all the time instances of the model are online: the time they spend setting up; the time they spend idle, waiting for requests; and the time they spend active, processing your requests. If you get a ton of traffic, we automatically scale up and down to handle the demand.
For fast booting models you'll only be billed for the time the model is active and processing your requests, so you won't pay for idle time like with other private models. Fast booting versions of models are labeled as such in the model's version list.
As with public models, if you would like more control over how a private model is run, you can use a deployments.
For a deeper dive, check out how billing works on Replicate.
If you need more support or have complex requirements, we can offer:
We've also got volume discounts for large amounts of spend. Email us at sales@replicate.com to learn more.