Overview

parafield · free tier
$42.10 creditsVerify attestation
Spend · this month
$18.40
42.10 credits left
Tokens
2.4 M
1.9M in · 0.5M out
Requests
12,840
last 30 days
Saved vs hosted APIs
~51%
$19.20 this month

Prompt privacy verify →

100%of your requests ran on
attested Apple hardware
hardware-attestedmodel digest-verifiedcode-attested · beta

The machine owner can't read your prompts — and you got the real model, not a substitute. Both are checkable in your own browser, no trust required.

Quick start

Point any OpenAI client or agent framework at Umbra. No new SDK.

# one base_url swap
client = OpenAI(
  base_url="https://api.umbra.dev/v1",
  api_key="umbra-7Xq…")

client.chat.completions.create(
  model="gemma-4-12b-coder",
  extra_body={"trust_level":"hardware"})

Models you're using browse catalog →

ModelRequestsTokensSpendIntegrity
gemma-4-12b-coder-fable5
Q4_K_M · coding fine-tune
9,1201.7M$10.20verified
llama-3.3-70b-uncensored
Q4 · abliterated
2,1400.5M$6.80verified
qwen3-32b-roleplay-v2
Q8 · creative
1,5800.2M$1.40verified