D

DeepInfra
Palo Alto, California-based AI infrastructure company founded 2022. Private. Operates in machine learning inference and cloud computing. Serves developers and enterprises with pay-per-use access to open-source LLMs, image, and audio models.
Plans tracked
3
no add-ons
Pricing changes
0
None published yet
Pricing model
Usage-based
No free tier
Pricing Change History
0 changesNo tracked pricing changes yet. New changes land here automatically.
Current plans
Checked
| Plan | Price |
|---|---|
| Pay as you go | Usage-based |
Also priced by usage
| |
| Custom LLMs (Dedicated GPUs) | Usage-based |
Also priced by usage
| |
| Dedicated Instances and Clusters | Contact |
Company Facts
How DeepInfra compares with its peers
| Company | Entry price |
|---|---|
T Together AILast change: Nov 11, 2026![]() | $3.99 per hour (H100) |
M ModalLast change: Oct 26, 2026![]() | $250 /mo |
B BasetenLast change: Nov 9, 2026![]() | $1 /mobilled annually |
A AnyscaleLast change: Jun 15, 2026![]() | Contact |
H HuggingfaceLast change: Nov 2, 2026![]() | $9 /mo |
L Lambda LabsLast change: Nov 9, 2026![]() | $0.69 per GPU per hour |
DeepInfra pricing FAQ
- How much does DeepInfra cost?
- DeepInfra prices on usage: the Pay as you go plan is $0.10 DeepSeek-V4.1-Flash-1017 - $ per 1M input tokens + $0.29 DeepSeek-V4.1-Flash-1017 - $ per 1M output tokens.
- Does DeepInfra have a free plan?
- No. DeepInfra does not list a free tier.
- What pricing model does DeepInfra use?
- DeepInfra uses usage-based pricing across 3 plans.
- What does “tracked since” mean?
- It's the date of the first saved copy of the pricing page that Pulse checked for changes against a later copy. For a few companies we hold older copies that Pulse never checked for changes, and those don't change this date. If Pulse has never checked two copies, it's the date of the first saved copy.
- Who are DeepInfra's pricing peers?
- Pulse compares DeepInfra with Together AI, Modal, Baseten, Anyscale, Huggingface and Lambda Labs.





