Loading Comparison
Fetching pricing data and provider information...
Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between RunPod and Together AI. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
Average Price Difference: $1.00/hour between comparable GPUs
| GPU Model ↑ | RunPod Price | Together AI Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A100 PCIE 40GB VRAM • RunPod | Not Available | — | ||
A100 PCIE 40GB VRAM • | ||||
A100 SXM 80GB VRAM • RunPodTogether AI | 2x GPU | ↓$0.51(39.0%) | ||
A100 SXM 80GB VRAM • $0.79/hour Updated: 4/18/2026 ★Best Price $1.30/hour 2x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.51(39.0%) | ||||
A2 16GB VRAM • RunPod | Not Available | — | ||
A2 16GB VRAM • | ||||
B200 192GB VRAM • RunPodTogether AI | ↑+$1.49(+33.2%) | |||
B200 192GB VRAM • $5.98/hour Updated: 4/18/2026 $4.49/hour Updated: 3/30/2026 ★Best Price Price Difference:↑+$1.49(+33.2%) | ||||
H100 NVL 94GB VRAM • RunPod | Not Available | — | ||
H100 NVL 94GB VRAM • | ||||
H100 PCIe 80GB VRAM • RunPod | Not Available | — | ||
H100 PCIe 80GB VRAM • | ||||
H100 SXM 80GB VRAM • RunPodTogether AI | 2x GPU | ↓$0.50(24.8%) | ||
H100 SXM 80GB VRAM • $1.50/hour Updated: 4/18/2026 ★Best Price $2.00/hour 2x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.50(24.8%) | ||||
H200 141GB VRAM • RunPodTogether AI | ↑+$1.00(+38.6%) | |||
H200 141GB VRAM • $3.59/hour Updated: 4/18/2026 $2.59/hour Updated: 3/30/2026 ★Best Price Price Difference:↑+$1.00(+38.6%) | ||||
HGX B300 288GB VRAM • RunPod | Not Available | — | ||
HGX B300 288GB VRAM • | ||||
L40 40GB VRAM • RunPodTogether AI | ↓$0.80(53.6%) | |||
L40 40GB VRAM • $0.69/hour Updated: 4/18/2026 ★Best Price $1.49/hour Updated: 4/18/2026 Price Difference:↓$0.80(53.6%) | ||||
L40S 48GB VRAM • RunPodTogether AI | ↓$1.70(81.0%) | |||
L40S 48GB VRAM • $0.40/hour Updated: 4/18/2026 ★Best Price $2.10/hour Updated: 4/18/2026 Price Difference:↓$1.70(81.0%) | ||||
RTX 3070 8GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3070 8GB VRAM • | ||||
RTX 3080 10GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3080 10GB VRAM • | ||||
RTX 3080 Ti 12GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3080 Ti 12GB VRAM • | ||||
RTX 3090 24GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3090 24GB VRAM • | ||||
A100 PCIE 40GB VRAM • RunPod | Not Available | — | ||
A100 PCIE 40GB VRAM • | ||||
A100 SXM 80GB VRAM • RunPodTogether AI | 2x GPU | ↓$0.51(39.0%) | ||
A100 SXM 80GB VRAM • $0.79/hour Updated: 4/18/2026 ★Best Price $1.30/hour 2x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.51(39.0%) | ||||
A2 16GB VRAM • RunPod | Not Available | — | ||
A2 16GB VRAM • | ||||
B200 192GB VRAM • RunPodTogether AI | ↑+$1.49(+33.2%) | |||
B200 192GB VRAM • $5.98/hour Updated: 4/18/2026 $4.49/hour Updated: 3/30/2026 ★Best Price Price Difference:↑+$1.49(+33.2%) | ||||
H100 NVL 94GB VRAM • RunPod | Not Available | — | ||
H100 NVL 94GB VRAM • | ||||
H100 PCIe 80GB VRAM • RunPod | Not Available | — | ||
H100 PCIe 80GB VRAM • | ||||
H100 SXM 80GB VRAM • RunPodTogether AI | 2x GPU | ↓$0.50(24.8%) | ||
H100 SXM 80GB VRAM • $1.50/hour Updated: 4/18/2026 ★Best Price $2.00/hour 2x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.50(24.8%) | ||||
H200 141GB VRAM • RunPodTogether AI | ↑+$1.00(+38.6%) | |||
H200 141GB VRAM • $3.59/hour Updated: 4/18/2026 $2.59/hour Updated: 3/30/2026 ★Best Price Price Difference:↑+$1.00(+38.6%) | ||||
HGX B300 288GB VRAM • RunPod | Not Available | — | ||
HGX B300 288GB VRAM • | ||||
L40 40GB VRAM • RunPodTogether AI | ↓$0.80(53.6%) | |||
L40 40GB VRAM • $0.69/hour Updated: 4/18/2026 ★Best Price $1.49/hour Updated: 4/18/2026 Price Difference:↓$0.80(53.6%) | ||||
L40S 48GB VRAM • RunPodTogether AI | ↓$1.70(81.0%) | |||
L40S 48GB VRAM • $0.40/hour Updated: 4/18/2026 ★Best Price $2.10/hour Updated: 4/18/2026 Price Difference:↓$1.70(81.0%) | ||||
RTX 3070 8GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3070 8GB VRAM • | ||||
RTX 3080 10GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3080 10GB VRAM • | ||||
RTX 3080 Ti 12GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3080 Ti 12GB VRAM • | ||||
RTX 3090 24GB VRAM • RunPod | 2x GPU | Not Available | — | |
RTX 3090 24GB VRAM • | ||||
Explore how these providers compare to other popular GPU cloud services
Compare RunPod with another leading provider
Compare RunPod with another leading provider
Compare RunPod with another leading provider
Compare RunPod with another leading provider
Compare RunPod with another leading provider
Compare RunPod with another leading provider
Access to a wide range of GPU types with enterprise-grade security
Only pay for the compute time you actually use
Programmatically manage your GPU instances via REST API
Pods typically ready in 20-30 s
SSH & VS Code tunnels built-in
Automatic migration on pre-empt
Access to Llama, DeepSeek, Qwen, and other leading open-source models
Pay-per-token API with OpenAI-compatible endpoints
LoRA and full fine-tuning with proprietary optimizations
Instant self-service or reserved dedicated clusters with H100, H200, B200, GB200, GB300 access
50% cost reduction for non-urgent inference workloads
Execute LLM-generated code in sandboxed environments
On‑demand single‑node GPU instances with flexible templates and storage.
Spin up multi‑node GPU clusters in minutes with auto networking.
Per-token pricing scales based on model size, from small open-source models to 405B parameter frontier models
50% discount for non-urgent inference workloads
Per-token pricing for LoRA and full fine-tuning based on model size and dataset
Hourly GPU pricing for instant self-service clusters
Custom pricing for reserved capacity with significant discounts for longer commitments
Single-tenant GPU instances with guaranteed performance
Sign up for RunPod using your email or GitHub account
Add a credit card or cryptocurrency payment method
Select a template and GPU type to launch your first instance
Sign up at together.ai
Generate an API key from your dashboard
Browse 100+ models for chat, code, images, video, and audio
Use OpenAI-compatible endpoints or Together SDK
Global data center network across 25+ cities with frontier hardware including GB300, GB200, B200, H200, H100
Documentation, community Discord, email support, and expert support for reserved cluster customers