Loading page
Deep Infra
Optimized inference for open-source models
Rapidly-catching neocloud🇺🇸 USinferenceopen-sourcebudget
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: September 17, 2026
Deep Infra pricing by GPU
Configurations, price rank, and alternatives for one GPU at a time.
LLM API Pricing
Pay-per-token pricing. Prices shown per 1M tokens.
Prices last updated: September 17, 2026
| Model | Input/1M | Output/1M | |||
|---|---|---|---|---|---|
| $0.019 | $0.030 | ||||
| $0.020 | $0.100 | ||||
| $0.030 | $0.120 | ||||
| $0.030 | $0.140 | ||||
| $0.050 | $0.100 | ||||
| $0.050 | $0.200 | ||||
| $0.050 | $0.150 | ||||
| $0.060 | $0.180 | ||||
| $0.060 | $0.180 | ||||
| $0.060 | $0.180 | ||||
Deep Infra pricing by model
Input, output, and batch rates, plus alternatives, for one model at a time.
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
- Infrastructure is US-based only, with no published international regions
- 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
Owned Inference Infrastructure
Runs on its own inference-optimized hardware in US-based data centers rather than rented capacity
Comprehensive AI APIs
Support for text generation, vision and OCR, embeddings and reranking, image, video and music generation, and speech recognition and synthesis
Batch API and Prompt Caching
Asynchronous batch endpoints with a files API, plus prompt caching billed at a reduced cached-input rate
Framework Integrations
Documented integrations for LangChain, LlamaIndex, the Vercel AI SDK, AutoGen, and the Anthropic SDK including Claude Code
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 Deep Infra's own inference infrastructure.
- Drop-in OpenAI replacement - swap base URL, keep existing code
- 100+ models including the DeepSeek V4, Qwen 3.7, Llama 4, Claude 5, Gemini 3.5, Gemma 4, GLM-5, Kimi K2.7, and Nemotron 3 families
- Comprehensive AI capabilities: text, vision, embeddings, image/video generation, speech
- Always-fresh model catalog with new releases deployed quickly
- Per-model service tiers (priority and flex) and a batch API for asynchronous jobs
Dedicated GPU Instances
On-demand GPU nodes with SSH access for custom workloads.
GPU Clusters
Multi-node B200 and B300 clusters with SSH access for training and full-control workloads.
- Rent a B200 or B300 cluster and run arbitrary workloads
- On-demand DGX B300 configurations billed per instance-hour
- Sold alongside dedicated instances via the pricing page and contact-sales flow
Private Model Deployments
Run your own fine-tuned weights on dedicated hardware behind a private endpoint.
- Deploy custom LLMs and LoRA adapters on A100, H100, H200, B200, or B300
- Autoscaling with a private endpoint for data isolation and compliance
Pricing Options
| Option | Details |
|---|---|
| Serverless pay-per-token | OpenAI-compatible inference APIs billed per input and output token, with no idle GPU time or minimums |
| Dedicated GPU hourly rates | Published transparent hourly pricing for A100, H100, H200, B200, and B300 GPUs with pay-as-you-go billing |
| Per-execution-time billing | Non-LLM models are billed for inference execution time rather than per token |
| Cached input pricing | Prompt-cached input tokens are billed at a lower rate than uncached input tokens |
| No long-term commitments | Flexible hourly billing for dedicated instances with no prepayments, contracts, or minimums required |
Availability & Support
Regions
Runs on self-operated, inference-optimized infrastructure in US-based data centers; no international region list is published.
Support
Documentation site, dashboard guidance, Discord community, feedback email (feedback@deepinfra.com), 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
Frequently Asked Questions
What GPU types does Deep Infra offer?
Deep Infra offers various GPU types including A100 SXM, H100 SXM, H200, HGX B300, B200. Check the pricing table above for current availability and pricing.
How do I get started with Deep Infra?
Create an account, Enable billing, Pick a GPU option, Launch and connect, Monitor usage
What are Deep Infra's main advantages?
Deep Infra's main advantages include: 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.
What are Deep Infra's limitations?
Deep Infra's main limitations include: Infrastructure is US-based only, with no published international regions, Primarily focused on inference and GPU rentals rather than broader cloud services, Newer player compared to established cloud providers.
Compare Providers
Find the best prices for the same GPUs and models from other providers
All Deep Infra Comparisons
Deep Infra vs 1LegionDeep Infra vs CivoDeep Infra vs CoreWeaveDeep Infra vs GPU OutletDeep Infra vs HyperstackDeep Infra vs Lium.ioDeep Infra vs LyceumDeep Infra vs Massed ComputeDeep Infra vs ModalDeep Infra vs Oracle CloudDeep Infra vs RunpodDeep Infra vs SpheronDeep Infra vs Vast.aiDeep Infra vs VerdaDeep Infra vs AtmosComputeDeep Infra vs GcoreDeep Infra vs gpu.aiDeep Infra vs Hexgrid CloudDeep Infra vs RuncrateDeep Infra vs SesterceDeep Infra vs ShadeformDeep Infra vs Together AIDeep Infra vs AceCloudDeep Infra vs Amazon AWSDeep Infra vs Compute CheapDeep Infra vs CrusoeDeep Infra vs DaytonaDeep Infra vs DigitalOceanDeep Infra vs GMI CloudDeep Infra vs Google CloudDeep Infra vs HyperbolicDeep Infra vs IO.NETDeep Infra vs Jarvis LabsDeep Infra vs Lambda LabsDeep Infra vs Microsoft AzureDeep Infra vs NebiusDeep Infra vs OblivusDeep Infra vs Omega GradientDeep Infra vs SeewebDeep Infra vs VultrDeep Infra vs Atlas CloudDeep Infra vs Denvr DataworksDeep Infra vs fal.aiDeep Infra vs KoyebDeep Infra vs Latitude.shDeep Infra vs Packet AIDeep Infra vs PaperspaceDeep Infra vs ScalewayDeep Infra vs TheAI CloudDeep Infra vs UpCloudDeep Infra vs AquanodeDeep Infra vs BentausDeep Infra vs Beyond.plDeep Infra vs Cudo ComputeDeep Infra vs Novita AIDeep Infra vs Theta EdgeCloudDeep Infra vs Thunder ComputeDeep Infra vs Voltage ParkDeep Infra vs ZettabyteDeep Infra vs Akamai CloudDeep Infra vs BeamDeep Infra vs EcoHashDeep Infra vs HinodeDeep Infra vs Hot AisleDeep Infra vs QuickPodDeep Infra vs Salad CloudDeep Infra vs SwissGPUDeep Infra vs OpenRouterDeep Infra vs VelokeyDeep Infra vs Fireworks AIDeep Infra vs GeoddDeep Infra vs AnthropicDeep Infra vs GroqDeep Infra vs CerebrasDeep Infra vs CohereDeep Infra vs Mistral AIDeep Infra vs OpenAIDeep Infra vs PerplexityDeep Infra vs Replicate