- Starting price
- $0.00300per minute of audio input
About DeepInfra
DeepInfra is an AI inference platform that provides a cloud for running ML models at scale using on-demand GPUs. It targets developers, data teams, and startups needing cost-efficient, high-performance model hosting and inference APIs.
Key Features
In practice, you need a reliable inference layer that supports multiple providers and predictable costs:
Model Catalog & APIs
Access a broad range of model types (Automatic Speech Recognition, Embeddings, Reranker, Text Generation, Text To Image, Text To Music, Text To Speech, Text To Video, World Model, Zero Shot Image Classification) via developer-friendly APIs.
Pricing & Usage Visibility
Published per-input and per-output rates enable cost planning with explicit examples (e.g., $0.10/M in, $0.95/M out; $1.30/M in, $2.60/M out).
GPU-backed Infrastructure
On-Demand NVIDIA DGX GPUs and other instances, with typical pricing around $4.89 per instance-hour to support scalable, low-latency inference.
Multi-provider Marketplace
A catalog featuring models from DeepSeek AI, Moonshot AI, Qwen, XiaomiMiMo, ZAI Org, NVIDIA, and more, with per-model pricing.
Summary
Best for ML engineers, data scientists, and startup product teams seeking scalable, cost-conscious model inference.
Pricing
View pricingPlans and prices as listed on deepinfra.com as of Sep 18, 2026.
Voxtral-Small-24B-2507
$0.00300 / per minute of audio input
Token Pricing for cached input
$0.0069 / per 1M cached input tokens
DeepSeek-V4-Flash-0731
$0.06 / per 1M input tokens
phi-4
$0.07 / per 1M input tokens
Mistral-Small-3.2-24B-Instruct-2506
$0.075 / per 1M input tokens
NVIDIA-Nemotron-3.5-Lightning
$0.08 / per 1M input tokens
DeepSeek-V4-Flash
$0.09 / per 1M input tokens
Llama-4-Scout-17B-16E
$0.10 / per 1M input tokens
Llama-4-Maverick-17B-128E
$0.20 / per 1M input tokens
Token Pricing
$0.2156 / per 1M input tokens
Qwen3.5-122B-A10B
$0.29 / per 1M input tokens
Qwen3.6-27B
$0.32 / per 1M input tokens
Qwen3.5-397B-A17B
$0.45 / per 1M input tokens
Token Pricing for output
$0.6468 / per 1M output tokens
Kimi-K2.7-Code
$0.68 / per 1M input tokens
Kimi-K2.6
$0.75 / per 1M input tokens
DeepSeek-V4-Pro
$1.30 / per 1M input tokens
Kimi-K3
$2.85 / per 1M input tokens
claude-opus-5
$5.00 / per 1M input tokens
The company behind DeepInfra
- Founded
- 2022
- Headquarters
- Palo Alto, United States
- Employees
- 11–50
- Total raised
- $125M
- Website
- deepinfra.com
- Social
- @DeepInfraLinkedIn
Alternatives to DeepInfra
See all →
The company behind DeepInfra
- Founded
- 2022
- Headquarters
- Palo Alto, United States
- Employees
- 11–50
- Total raised
- $125M
- Website
- deepinfra.com
- Social
- @DeepInfraLinkedIn
DeepInfra Reviews
No reviews yet. Used DeepInfra? Be the first to review it.