Deep Infra
Optimized inference for open-source models
Last reviewed Mar 14, 2026
Deep Infra is an AI inference cloud that provides serverless APIs for 100+ models and dedicated GPU rentals. Features OpenAI-compatible endpoints, custom model deployments, and infrastructure optimized for scale.
Available GPUs
Hourly on-demand pricing. Click column headers to sort.
Prices last updated: June 19, 2026
LLM API Pricing
Pay-per-token pricing. Prices shown per 1M tokens.
Prices last updated: June 19, 2026
| Model | Creator | Context | Input/1M | Output/1M | Updated |
|---|---|---|---|---|---|
| Mistral | 131K | $0.020 | $0.040 | 6/19/2026 | |
| Meta | 128K | $0.020 | $0.030 | 6/19/2026 | |
| OpenAI | 128K | $0.030 | $0.140 | 6/19/2026 | |
| NVIDIA | 131K | $0.040 | $0.160 | 6/4/2026 | |
| Mistral | 32K | $0.050 | $0.080 | 6/19/2026 | |
| 131K | $0.050 | $0.100 | 6/19/2026 | ||
| NVIDIA | 262K | $0.050 | $0.200 | 6/19/2026 | |
| 131K | $0.050 | $0.150 | 6/19/2026 | ||
| 262K | $0.070 | $0.340 | 6/19/2026 | ||
| Microsoft | 16K | $0.070 | $0.140 | 6/19/2026 | |
Pros & Cons
Advantages
- Simple OpenAI-compatible API alongside controllable GPU rentals
- Competitive hourly rates for flagship NVIDIA GPUs including latest B200 and B300
- Fast provisioning with SSH access for dedicated instances (ready in ~10 seconds)
- Supports custom deployments in addition to hosted public models
Limitations
- Region list is not clearly published in the public marketing pages
- Primarily focused on inference and GPU rentals rather than broader cloud services
- Newer player compared to established cloud providers
Key Features
Drop-in OpenAI Replacement
OpenAI-compatible API for 100+ models including DeepSeek, Qwen, Llama 4, Claude, and Gemini families with autoscaling
Dedicated GPU Rentals
B200 instances with SSH access spin up in about 10 seconds and bill hourly
Custom LLM Deployments
Deploy your own Hugging Face models onto dedicated A100, H100, H200, B200, or B300 GPUs
Transparent GPU Pricing
Published per-GPU hourly rates for A100, H100, H200, B200, and B300 with competitive pricing
Inference-Optimized Hardware
All hosted models run on H100 or A100 hardware tuned for low latency
Comprehensive AI APIs
Support for text generation, vision and OCR, embeddings and reranking, image and video generation, and speech recognition
SOC 2 & ISO 27001 Compliance
Zero retention policy with enterprise-grade security certifications for data privacy and protection
Compute Services
Serverless Inference
Hosted model APIs with autoscaling on H100/A100 hardware.
- Drop-in OpenAI replacement - swap base URL, keep existing code
- 100+ models including latest DeepSeek V4, Qwen 3, Llama 4, Claude 4.5, and Gemini 3 families
- Comprehensive AI capabilities: text, vision, embeddings, image/video generation, speech
- Always-fresh model catalog with new releases deployed quickly
Dedicated GPU Instances
On-demand GPU nodes with SSH access for custom workloads.
Pricing Options
| Option | Details |
|---|---|
| Serverless pay-per-token | OpenAI-compatible inference APIs with pay-per-request billing on H100/A100 hardware |
| Dedicated GPU hourly rates | Published transparent hourly pricing for A100, H100, H200, B200, and B300 GPUs with pay-as-you-go billing |
| No long-term commitments | Flexible hourly billing for dedicated instances with no prepayments or contracts required |
Availability & Support
Regions
Region list not published on the GPU Instances page; promo mentions Nebraska availability alongside multi-region autoscaling messaging.
Support
Documentation site, dashboard guidance, Discord community link, and contact-sales options.
Getting Started
- 1
Create an account
Sign up (GitHub-supported) and open the Deep Infra dashboard
- 2
Enable billing
Add a payment method to unlock GPU rentals and API usage
- 3
Pick a GPU option
Choose serverless APIs or dedicated A100, H100, H200, B200, or B300 instances
- 4
Launch and connect
Start instances with SSH access or call the OpenAI-compatible API endpoints
- 5
Monitor usage
Track spend and instance status from the dashboard and shut down when idle
Compare Providers
Find the best prices for the same GPUs from other providers
