DeepInfra pricing and offerings | DeployCue Skip to content
DeployCue
DeepInfra logo

DeepInfra

DeepInfra offers rock-bottom priced hosted inference across a wide catalog of open-weight models, often undercutting competitors by 50-80%. With per-token billing as low as $0.03/M input on small models and aggressive pricing on DeepSeek V3 and Llama 70B, it is the cost champion for high-volume, budget-sensitive inference workloads.

Headquarters
United States
Founded
2022
LLM inference from
$0.050/M tokens
Offerings
4
Countries
1
Categories: LLM inference
Free tier
No
Free credits
-
Card required
No
API
Yes
CLI
Yes
Terraform
No
SLA uptime
-

LLM inference

Compare all →

From $0.050

4 results

Provider Plan Price Regions Visit
DeepInfra DeepSeek V3 $0.890 $0.490 128K $0.890 /M tokens
Input $0.490/1M tokens
Verified
Global Visit →
DeepInfra Llama 3.1 8B $0.050 $0.030 128K $0.050 /M tokens
Input $0.030/1M tokens
Verified
Global Visit →
DeepInfra Llama 3.3 70B $0.400 $0.230 128K $0.400 /M tokens
Input $0.230/1M tokens
Verified
Global Visit →
DeepInfra Qwen 2.5 72B $0.400 $0.130 131K $0.400 /M tokens
Input $0.130/1M tokens
Verified
Global Visit →

Datacenter countries (1)

Compare with rivals

Similar providers

Hetzner logo 7

Hetzner is a German hosting institution renowned for delivering the best price-to-performance ratio in Europe - cloud servers from €4/mo, bare-metal from €52/mo, and block storage at €0.04/GB. With data centers in Germany, Finland, and the US, a generous free tier, and ultra-low €0.0012/GB egress, it is the value benchmark for VPS and dedicated hosting.

Amazon Web Services is the world's largest cloud provider with 200+ services across compute, storage, databases, ML, and networking. Dominates in enterprise with the broadest global region footprint and the deepest service catalog, but pricing complexity and egress fees add up at scale.

Anthropic logo 2

Anthropic's API delivers the Claude model family - Opus, Sonnet, and Haiku - known for thoughtful reasoning, strong coding ability, and industry-leading safety alignment. With a 200K context window and a reputation for nuanced, instruction-following output, Claude is the preferred model for complex analytical and creative tasks.

Cloudflare operates the world's largest edge network spanning 330+ cities with a famously generous free CDN tier that includes unmetered DDoS protection, a global anycast network, and the Workers serverless platform. With R2 object storage, AI inference, and a complete application-services portfolio, it has evolved from a CDN into the internet's front door.

OpenAI logo 2

OpenAI's API is the gold standard for frontier LLM access, serving the flagship GPT-5 family alongside the cost-efficient GPT-4.1 and GPT-4.1 nano tiers. With 400K+ context windows, function calling, structured outputs, and a massive developer ecosystem, it powers the majority of production AI applications worldwide.

Backblaze B2 is the value leader in S3-compatible cloud storage at $0.006/GB-month - roughly one-quarter the cost of AWS S3 Standard - with free egress to Cloudflare, Fastly, and other CDN partners. Founded on a mission of affordable, transparent storage, it is the default choice for backups, media archives, and cost-conscious object storage workloads.

Frequently asked questions

What does DeepInfra offer?
DeepInfra publishes pricing across 1 product categories we track, listed by category below with per-unit pricing, specs, and region coverage.
How much does DeepInfra cost?
Each category section below shows DeepInfra's starting price and the full plan lineup. Prices are in USD and link straight to the provider.
Does DeepInfra have a free tier?
The facts panel shows whether DeepInfra offers a free tier, free credits, and whether a credit card is required to sign up.
Where are DeepInfra's datacenters?
The datacenter countries section lists every country where DeepInfra operates capacity that we have recorded, so you can pick a region near your users.
Is DeepInfra cheaper than the major clouds?
It depends on the product. Use the comparison links below to put DeepInfra head to head with rivals and see where it wins on price and where it does not.
How do I sign up for DeepInfra?
Use the visit button to go straight to DeepInfra. The facts panel notes whether a credit card or KYC is required and whether provisioning is instant.