# DeepInfra

> Low-cost inference API for open models.

DeepInfra has a SharkScore of 59.1/100, ranked #52 of 273 in Model APIs & inference (updated 2026-11-19).

- Website: https://deepinfra.com (deepinfra.com)
- Kind: Tool · Pricing: Paid
- Maker: DeepInfra
- Categories: Model APIs & inference
- Verified by the maker: no

## Why it scores 59.1

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 32 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 65 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Model APIs & inference.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | #56.4K |
| GitHub stars | — |
| Stars, last 90 days | — |
| Downloads, 30 days | — |
| Reviews | none yet |
| Last update | — |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / no / yes / yes |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, DeepInfra is a model inference API and GPU service with per-model usage pricing rather than a stated monthly subscription. [E2, E3]

DeepInfra offers hosted inference for language, vision, embeddings, image and video generation, and speech models, plus private model deployments and GPU rental. Its docs describe an OpenAI-compatible API. [E3]

### Pros

- The docs describe an OpenAI-compatible API and give a base URL for using it with the OpenAI SDK. [E3]
- The vendor lists several model categories and private deployment and GPU rental options. [E3]

### Cons

- The pricing page describes different billing methods by model, and the supplied evidence does not state a fixed monthly subscription price. [E2]
- Free-tier and trial terms are not stated in the supplied pages. [E1, E2, E3]
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| Model-dependent usage pricing | Varies by model and billing method; examples below are per 1M tokens. | Some language models are billed per token; most other models are billed for inference execution time. |
| DeepSeek-V4-Flash-0731 | $0.06 per 1M input tokens; $0.18 per 1M output tokens | 1024k context. |
| Meta-Llama-3.1-8B-Instruct-Turbo | $0.02 per 1M input tokens; $0.04 per 1M output tokens | 128k context. |
| Kimi-K3 | $2.85 per 1M input tokens; $14.25 per 1M output tokens | 1024k context. |
| Voxtral-Mini-3B-2507 | $0.00100 per minute of audio input | Audio input pricing. |
| On-Demand DGX B300 GPUs | $5.89 per instance-hour | Instance-hour pricing. |

Checked 2026-11-18 · https://deepinfra.com/pricing

### Sources

- https://deepinfra.com/ (fetched 2026-11-18)
- https://deepinfra.com/pricing (fetched 2026-11-18)
- https://docs.deepinfra.com/ (fetched 2026-11-18)
- https://deepinfra.com/privacy (fetched 2026-11-18)
- https://deepinfra.com/terms (fetched 2026-11-18)
- https://trust.deepinfra.com/ (fetched 2026-11-18)

## Top alternatives

1. [Hugging Face](https://rankshark.pro/tools/hugging-face) — SharkScore 79.3. The home of open models, datasets and Spaces.
2. [Claude Platform](https://rankshark.pro/tools/anthropic-api) — SharkScore 77.5. API for building with Claude models.
3. [LiteLLM](https://rankshark.pro/tools/litellm) — SharkScore 76.1. Proxy and SDK to call 100+ LLM APIs in the OpenAI format.
4. [Vertex AI](https://rankshark.pro/tools/vertex-ai) — SharkScore 75.7. Google Cloud's platform to build with Gemini and other models.
5. [OpenAI API](https://rankshark.pro/tools/openai-api) — SharkScore 75.3. API for GPT, image, audio and embedding models.

---
Source: https://rankshark.pro/tools/deepinfra · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
