DeepInfra

Cloud

Affordable GPU cloud for open AI models. Serverless and dedicated instances.

Provider Info

"API Env Var" DEEPINFRA_API_KEY

"Rate Limits" 200 concurrent requests

Llama 3.1 70B

Llama 3.3 70B

Qwen 2.5 72B

Mistral 8x7B

Mixtral 8x22B

Free

$0/mo

200 concurrent requests

All models · Standard concurrency

Pay-as-you-go

$0/mo

Per-token pricing

All models · Higher concurrency

Pro

$49.00/mo

10x higher concurrency

All models · Priority support

"Free Tier Available"

200 concurrent requests, no credit card — No credit card required

STARTUP50

$50 free credits for startups

"Get deal →"