Build with Umbra

A familiar API boundary.

Use OpenAI-compatible clients with Umbra's model registry. Your API key authorizes requests; prompts are never logged.

Your API keys.

Create persistent keys for the OpenAI-compatible API. Keys are revocable and the full value is kept only in this browser. The server stores a short-lived revocation entry, not the key itself.

The full key is returned once and saved only in this browser. Clearing local data removes your saved copy.

Loading local keys…

In self-hosted deployments, signing a token with UMBRA_API_SECRET still works for direct administration. Local development without that secret uses an ephemeral process secret.

Holder tier.

Holder tiers and tier-based API quotas are active for $UMBRA on Ethereum.

Holder tier

$UMBRA tier

Reading your balance needs no signature and sends nothing to Umbra. Verifying ownership signs a message — no gas, no transaction — so your API keys get your tier's quota and your tier's enforced benefits. Holder-rate credits are enforced on on-chain top-ups; early access and votes are live at /vote.

Verification is signed proof, not a transaction. It enforces your tier's API quota, Council seats, chat and UmbraCode token ceilings, priority routing, and holder-rate credits on on-chain top-ups. Early access and votes are available at /vote.

Tier ladder

Whole-token thresholds

Base0 $UMBRA

Holder100,000 $UMBRA

Circle1,000,000 $UMBRA

Council10,000,000 $UMBRA

Chat completions.

curl https://{your-domain}/api/agent/v1/chat/completions \
  -H "Authorization: Bearer $UMBRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"umbra-auto","stream":true,"messages":[{"role":"user","content":"Hello"}]}'

from openai import OpenAI

client = OpenAI(
    base_url="https://{your-domain}/api/agent/v1",
    api_key=os.environ["UMBRA_API_KEY"],
)
response = client.chat.completions.create(
    model="umbra-auto",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

The base URL is /api/agent/v1 relative to your Umbra host. Set it from your deployment origin rather than hardcoding a local port.

Privacy boundary: server-side redaction is not applied to API calls. Client applications own redaction before sending requests to this endpoint.

Models and indicative credits.

Model	Context	Input / 1M	Output / 1M
Umbra Auto A balanced route selected for your prompt	128,000	0.15 cr	0.60 cr
Nova 4 Fast, capable everyday reasoning	128,000	2.50 cr	10.00 cr
Sage Sonnet Careful writing and analysis	200,000	3.00 cr	15.00 cr
Reasoning R1 Deep, deliberate problem solving	65,536	0.55 cr	2.19 cr
Gemini Flash Multimodal speed with a large context	1,000,000	0.10 cr	0.40 cr
Qwen Coder Focused help for code and debugging	262,144	0.30 cr	1.00 cr
Llama Open Open-weight conversation	131,072	0.40 cr	0.40 cr
Mistral Small Efficient and precise	32,000	0.10 cr	0.30 cr
Venice Private Private, uncensored Venice flagship	128,000	0.20 cr	0.90 cr
Venice Flash Fast inference with a very large context	1,048,576	0.15 cr	0.50 cr
Venice Deep Deliberate reasoning for difficult work	200,000	1.54 cr	4.84 cr

Credits are indicative local test pricing. On-chain funding is not connected in this MVP.