Baseten vs RunPod
- GPUs
- 6 43
- Cheapest GPU
- $0.63/hr $0.13/hr
- Price wins
- 0/4 4/4
RunPod is cheaper on all 4 GPUs both rent. RunPod carries 37 more GPUs.
Runs dedicated model inference billed per minute of GPU time, plus pre-optimised model APIs billed per token.
Best for: Production inference for custom models
GPU cloud that rents pods billed per second and runs serverless endpoints, with community and secure hosting tiers.
Best for: Serverless inference and cheap GPU pods
Price by GPU
The 4 GPUs both rent. Cheapest live rate per GPU-hour, most powerful first. The cheaper side is in purple.
| GPU | Baseten | RunPod | Gap |
|---|---|---|---|
| NVIDIA B200 SXM 180GB | $9.98/hr | $6.79/hr | 47% |
| NVIDIA H100 SXM5 80GB | $6.50/hr | $3.49/hr | 86% |
| NVIDIA A100 SXM4 80GB | $4.00/hr | $1.59/hr | 152% |
| NVIDIA L4 24GB | $0.85/hr | $0.49/hr | 73% |
Prices last checked: Baseten 1 Oct 2026, RunPod 1 Oct 2026.
Only on one side
Only on Baseten 2
Only on RunPod 39
- NVIDIA B300 SXM 262GB $7.89
- AMD Instinct MI300X 192GB $2.39
- NVIDIA H200 SXM 141GB $4.59
- NVIDIA H100 NVL 94GB $3.19
- NVIDIA H200 NVL 141GB $3.79
- NVIDIA H100 PCIe 80GB $2.89
- NVIDIA RTX PRO 6000 Blackwell Workstation Edition $2.19
- NVIDIA RTX PRO 6000 Blackwell Server Edition $0.59
- NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition $0.50
- NVIDIA GeForce RTX 5090 32GB $0.99
- NVIDIA RTX 6000 Ada 48GB $0.84
- NVIDIA L40S 48GB $1.09
- NVIDIA A100 PCIe 80GB $1.59
- NVIDIA A100 SXM4 40GB $1.00
- NVIDIA RTX 5000 Ada 32GB $0.83
- NVIDIA RTX PRO 5000 Blackwell 48GB $0.96
- NVIDIA GeForce RTX 5080 16GB $0.59
- NVIDIA RTX PRO 4500 Blackwell 32GB $0.72
- +21 more on the RunPod page
Company facts
| Fact | Baseten | RunPod |
|---|---|---|
| Headquarters |  San Francisco, CA | United States |
| Type | GPU cloud | GPU cloud |
| Founded | n/a | 2022 |
| GPUs priced | 6 | 43 |
| Fastest GPU | NVIDIA B200 SXM 180GB | NVIDIA B200 SXM 180GB |
| Services | Dedicated model inference, pre-optimised model APIs, training (Loops SDK), self-hosted deployment | n/a |
| Pricing models | Per-minute GPU compute, per-token for model APIs | n/a |
Compliance
Frameworks each provider states it holds, linked to its own statement. Not published means we found no statement, not that the provider fails it. Check the scope with the provider.
Pick your provider
Questions
- What is the difference between Baseten and RunPod?
- Baseten: Runs dedicated model inference billed per minute of GPU time, plus pre-optimised model APIs billed per token. RunPod: GPU cloud that rents pods billed per second and runs serverless endpoints, with community and secure hosting tiers.
- Is Baseten cheaper than RunPod?
- RunPod is cheaper on all 4 GPUs both rent. RunPod carries 37 more GPUs.
- How much does a NVIDIA B200 SXM 180GB cost on Baseten and RunPod?
- Baseten charges $9.98 per GPU-hour and RunPod charges $6.79 per GPU-hour, the cheapest live rate on each.
- Which GPUs can I rent on both Baseten and RunPod?
- 4 GPUs, including NVIDIA B200 SXM 180GB, NVIDIA H100 SXM5 80GB, NVIDIA A100 SXM4 80GB, NVIDIA L4 24GB.
- How are these prices compared?
- Each figure is the cheapest live rate per GPU-hour for that GPU. We use on-demand pricing where a provider sells it and fall back to community or reserved terms, labelled, where that is all they sell. Spot capacity is left out because it can be reclaimed. Rates are refreshed by our daily ingest.
How we define a live price: methodology.
