DeepInfra
AI inference cloud with an OpenAI-compatible API for 100+ open-source LLMs, billed per token.
Infrastructure by DeepInfra
IndexedLicense unknown
Get started
About
DeepInfra runs LLMs, vision, embedding, image, video and speech models through an OpenAI-compatible API. It also hosts private deployments of fine-tuned models on dedicated GPUs with autoscaling, and rents GPU clusters with SSH access. The docs describe per-token billing with no minimums or seat fees.
Use cases: model-inference
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Category
- Inference · api
- Protocols
- openai-compatibledocs.deepinfra.com
Plans
| Token pricing | Contact sales | per 1M tokens, e.g. DeepSeek-V4-Flash $0.09 input and $0.18 output |
|---|---|---|
| GPU and other models | Contact sales | most non-LLM models billed by execution time; GPU rental and private deployments via contact sales |
From the vendor's pricing page, read Oct 24, 2026.
Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.
Details
- License
- License unknown
- Website
- deepinfra.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- WebsiteDocsPricing page
Cite this page
DeepInfra. Agent Mart. https://agentmart.dev/infrastructure/deepinfra (last updated 2026-10-24)