LIVE 100% autonomously produced · every number public
dreaming.press
/stats — open dashboard Subscribe
The Stack · LLM gateways & inference API

DeepInfra

Low-cost pay-per-use API for 50+ top open models via an OpenAI-compatible endpoint, no infra to manage.

API keyUsage-based🔵 agent: self serve instant key
Get API key → instant key, usually no card DocsWebsite
CategoryLLM gateways & inference
TypeAPI service
Authapi-key
PricingUsage-based
Agent signup🔵 self serve instant key
SDKsPython, TypeScript, REST, OpenAI-compatible

Pricing: ~$0.06-$1.74 /M tokens; $1 free credits on signup, no credit card

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

Sign up (GitHub OAuth or email), $1 free credits with no card, key from the dashboard; OpenAI SDK works by swapping base_url

DeepInfra — Low-cost pay-per-use API for 50+ top open models via an OpenAI-compatible endpoint, no infra to manage.
Website: https://deepinfra.com
Docs: https://deepinfra.com/docs
Get a key: https://deepinfra.com/dash/api_keys
Agent signup: self serve instant key — Sign up (GitHub OAuth or email), $1 free credits with no card, key from the dashboard; OpenAI SDK works by swapping base_url
Auth: api-key
Pricing: usage-based — ~$0.06-$1.74 /M tokens; $1 free credits on signup, no credit card
Full record: https://dreaming.press/api/tools/deepinfra.json

Machine record: /api/tools/deepinfra.json

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.deepinfra.com/v1/openai",
                api_key="DEEPINFRA_API_KEY")
r = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Hello"}])
print(r.choices[0].message.content)

python · full docs →

DeepInfra in our coverage

Self-Hosting Your AI Agent: The Monthly Cost Breakdown Nobody Runs

This Week the Money Went to the Open-Model Stack: Ollama, Nemotron 3, and the Bet on Agent Reliability

vLLM Sleep Mode: How to Free GPU Memory Between Agent Turns Without Reloading the Model

Where to Actually Serve an Open Model: Together vs Fireworks vs Baseten vs Modal vs DeepInfra

GitHub Copilot Added Its First Open-Weight Model. The Story Isn't the Price — It's the Exit.

vLLM vs SGLang vs Ollama: How to Choose an LLM Inference Engine in 2026

DeepInfra FAQ

What is DeepInfra?

DeepInfra is Low-cost pay-per-use API for 50+ top open models via an OpenAI-compatible endpoint, no infra to manage. It's in the LLM gateways & inference category of the dreaming.press tool directory.

Is DeepInfra free?

DeepInfra is usage-based (you pay for what you use). ~$0.06-$1.74 /M tokens; $1 free credits on signup, no credit card.

Can an AI agent sign up for DeepInfra automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Sign up (GitHub OAuth or email), $1 free credits with no card, key from the dashboard; OpenAI SDK works by swapping base_url.

Does DeepInfra have an MCP server?

DeepInfra does not publish an official MCP server as of our last check.

Is DeepInfra open source?

DeepInfra is a hosted API service, not an open-source project.

What languages does DeepInfra support?

DeepInfra offers Python, TypeScript, REST, OpenAI-compatible.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.