DeepInfra Inference API
Hosted API serving open-weight models for text generation, embeddings, reranking, image, video, speech and music, billed per token for language models and by inference time for most others, with a batch API, private and custom-model deployment and LoRA adapters; per-token rates are listed on the pricing page, with no long-term contracts or upfront costs.
Find alternatives to DeepInfra Inference API
What it does
- Model inference
- Model hosting
Features 2
- Zero retention policyKeeps inputs, outputs and user data private under a zero retention policy
- Live inference metricsShows live speed, scale and stability metrics for the service
Sources
- Pricing
-
Pricing page: "Some of our langauge models offer per token pricing. Most other models are billed for inference execution time."; home page lists rates such as DeepSeek-V4-Flash-0731 "$0.06/M in • $0.18/M out".
- Description
-
Official documentation · 6 Nov 2026
Home page: "Accelerate your AI with developer-friendly APIs designed for performance and cost-efficiency."
- What it does
-
Official documentation · 6 Nov 2026
Home page: "Accelerate your AI with developer-friendly APIs designed for performance and cost-efficiency."
- Sold within
-
Pricing page publishes per-token and per-execution-time rates with no contract.
- Name
-
Official documentation · 6 Nov 2026
Name as published on the product page.
- URL
-
Official documentation · 6 Nov 2026
Product page, read 2026-11-06.
- Deployment
-
Official documentation · 6 Nov 2026
Vendor-run inference service; docs list private-model deployment, and no self-hosted option is named on the pages read.
- Interfaces
-
Official documentation · 6 Nov 2026
Vendor-run inference service; docs list private-model deployment, and no self-hosted option is named on the pages read.
Also from DeepInfra
-
DeepInfra GPU Instances Infrastructure service
On-demand NVIDIA GPU containers from DeepInfra, started in under ten seconds with a chosen base image such as PyTorch or CUDA and reached over SSH, for training, fine-tuning or running inference, billed by the hour with no minimums (a single B200 at $4.89 an hour on the page read).
-
DeepInfra Custom LLMs Infrastructure service
Dedicated hosting on DeepInfra for a customer's own model: the model runs on dedicated NVIDIA A100, H100, H200, B200 or B300 GPUs with automatic scaling, billed by the minute and invoiced weekly at a per-GPU-hour rate (A100 $1.49 to B300 $5.89 on the page read).
-
DeepCluster Infrastructure service
A dedicated NVIDIA Blackwell B300 GPU cluster that DeepInfra designs, procures, deploys in a Tier 3 datacenter and operates for the customer, who owns the hardware, on a three- to five-year contract; the page quotes $2.99 per GPU-hour all-in on a three-year term and 256 to 5,000 GPUs, through sales.
Open DeepInfra in the directory
Something wrong here? Send a correction — quote this product id: deepinfra-inference-api.