official

DeepInfra API

A hosted inference platform offering a catalog of language, embedding, image, speech, and other models through developer APIs.

Visit official website
Provider profile

The facts, with sources.

Provider typeofficial
Pricing modelPricing is specific to each model and billing unit; some tagged language models also have documented standard, priority, or flex service tiers.
Markup notesPlatform-published model pricing; service tiers and workload units prevent a single universal comparison.
OpenAI compatibilityyes
DeepInfra documents an OpenAI-compatible chat completions endpoint using its base URL, API token, and catalog model names.
Model supportThe public model catalog lists currently hosted models across multiple inference categories; consult each model page for capabilities and limits.
Payment methodsNot verified
Supported regionsNot verified — check official availability documentation
Billing currenciesUSD
Last reviewed2026-10-24 UTC

Verified considerations

Documented advantages

  • Public model-specific catalog and pricing pages.
  • Documented OpenAI-compatible chat completions integration.

Limitations to check

  • Billing units and service-tier availability differ by model.
  • OpenAI-compatible chat completions do not imply identical support for every model type or API feature.

Official sources

See outdated or incorrect information? Send a correction.