Home/大语言模型/DeepInfra API

DeepInfra API

DeepInfra 接口

Open-source model hosting with per-token pricing. Llama, Qwen, Whisper, and Stable Diffusion.

开源模型托管，按 token 计费。Llama、Qwen、Whisper 和 Stable Diffusion。

Website

https://deepinfra.com

Documentation

https://deepinfra.com/docs

Pricing

pay-as-you-go (from $0.05/1M tokens)

Authentication

API Key

Popularity

60/100

Endpoints

https://api.deepinfra.com/v1/openai/chat/completions

SDKs

PythonOpenAI SDK compatible

Tags

llmopen-sourcehosting

Last updated: 2026-08-01

Compare DeepInfra API with other APIs

Similar APIs

Access GPT-4o, GPT-4, GPT-3.5, embeddings, DALL-E, Whisper, and TTS models via REST API.

GitHub REST API

Manage repos, issues, PRs, actions, and users. The backbone of open-source automation.

Hugging Face Hub API

Access 500K+ models, datasets, and Spaces. Inference API for instant model deployment.

LangChain Platform

Framework and platform for building LLM applications. LangSmith for observability, LangServe for deployment.

Something wrong or missing? Open an issue on GitHub →

Pricing Comparison

API	Pricing	Auth	Popularity
OpenAI API	pay-as-you-go (per token)	API Key (Bearer Token)	100
Anthropic Claude API	pay-as-you-go (per token)	API Key (x-api-key header)	87
Google Gemini API	free tier available, pay-as-you-go	API Key	85
OpenAI Assistants API	pay-as-you-go (per token + per tool use)	API Key (Bearer Token)	84

Discussion

Questions, feedback, or suggestions? Start a discussion.

Discuss on GitHub