Skip to content
NGARi
Buy NGARi+

NGARi Inference API

Bison Venture Partners LLC dba NGARi · v1 · Zero retention · Attested

The API serves qwen3.8-orin — a 27.3B sovereign model (Apache 2.0) running on our own edge hardware (NVIDIA Jetson AGX Orin) with no third-party model provider in the path. We store nothing. No prompt or response is ever written to disk. Every request is metered against your prepaid balance and recorded as a signed attestation you can verify.

Cloud models — separate lane

The sovereign /v1 lane stays on-device and zero-retention. Frontier cloud models run on a separate lane at https://api.ngari.ai/v1/cloud. Cloud requests leave our hardware, are processed by the named provider, and are subject to that provider's retention terms. They are not zero-retention and carry no attestation claim.

ModelProviderInput / 1MOutput / 1MCached input / 1M
ngari-cloud-flashDeepSeek Flash$0.50$2.00$0.06
ngari-cloud-proDeepSeek V4-Pro$2.10$6.30$0.25
ngari-cloud-kimiKimi K3.1 Pro$4.00$16.00$0.50

Cloud credits are separate from local API credits. Create a key first, then buy USD credits with the same email:

Buy $20 cloud credits   Buy $100 cloud credits

Credits settle to your key by email within ~5 minutes. The API charges actual input/output/cache tokens; each response carries the model, provider, privacy label and cost. A low provider balance pauses the lane rather than silently failing.

POST https://api.ngari.ai/v1/cloud/chat/completions
Authorization: Bearer ngari_...
Content-Type: application/json

{"model":"ngari-cloud-flash","messages":[{"role":"user","content":"Hello"}]}

GET /v1/cloud/models lists live models and prices. See the Privacy Policy for cloud processing and the Terms for acceptable use. Do not send regulated or sensitive data to the cloud lane without a written agreement.

Get an API key

Enter the email you will use for billing. We show your key once; it is stored only in this browser.

Models

ModelRoleNotes
qwen3.8-orinDefault — preview + API27.3B (Q4_K_M), Apache 2.0. Served on-device; no third-party model provider in the path.
ngari-ft-distilled-v5Distilled line — not served publicly1.5B, Apache 2.0, fine-tuned by NGARi. Retired from the public path: asked to ground on a long facts block it confabulated details about our own programs, so the 27B is served instead.

The served model is pinned per deployment. GET /api/health reports the live model tag, whether it is resident, and the memory gate — so you can always verify what you are calling rather than trust a page.

Model weights for the NGARi-distilled line are published Apache 2.0 at huggingface.co/NGARiAI. The hosted API runs qwen3.8-orin on-device; to run the same model on hardware you own, see NGARi+ hardware.

Endpoint

POST https://ngari.ai/api/chat

OpenAI-compatible endpoint (self-hosted)

On a NGARi device the sovereign model backend also speaks the OpenAI wire format at http://127.0.0.1:11438/v1, so any OpenAI-compatible harness — OpenClaw, Hermes Agent, DeepSeek Harness, the OpenAI SDK, opencode — can run on local, on-device intelligence.

POST http://127.0.0.1:11438/v1/chat/completions
GET  http://127.0.0.1:11438/v1/models

Point your client’s base URL at it. Loopback clients need no key; a ngari_ Bearer key is required for any non-local client and meters usage exactly like the public API. Completed requests return a signed attestation receipt (header X-NGARi-Attestation, or an SSE comment on streams) and appear under GET /v1/attestations. This is the layer a plain open-source harness cannot provide: on-device inference plus a verifiable proof of where it ran.

Authentication

Pass your key as a Bearer token. Keys start with ngari_ and are shown only once at creation. We store only a hash — lost keys cannot be recovered (create a new one).

Authorization: Bearer ngari_your_key_here

Example

curl https://ngari.ai/api/chat \
  -H "Authorization: Bearer ngari_..." \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Explain sovereign AI in two sentences."}]}'

The response is an SSE stream: a first event carries {"model":...}, then {"delta":"..."} chunks, then [DONE].

Key management

OperationEndpoint
Create key (email = billing identity)POST /api/keys {"email":"you@..."}
Balance + usageGET /api/keys/me (Bearer)
Signed attestation receiptsGET /api/keys/attestations (Bearer)

Pricing

PackCreditsTokensLink
$1500500Kbuy.stripe.com/cNi4gz45M4tUc35d1ubMQ1J
$52,5002.5Mbuy.stripe.com/28EaEXfOu1hI7MP0eIbMQ1z
$2010,00010Mbuy.stripe.com/cNiaEX31If8yffhd1ubMQ1A
$10050,00050Mbuy.stripe.com/6oU5kD6dUbWm5EH9PibMQ1B

1 credit = 1,000 tokens · $2.00 per 1M tokens. Credits are charged on actual usage (an up-front budget is reserved per request and the unused remainder refunded automatically). Credits never expire. Unused credits are refundable within 14 days of purchase — email support@ngari.ai.

Purchases settle to your key by email: buy credits with the same email you used to create your key, and the balance appears within ~5 minutes.

Rate limits

The attestation receipt

Each paid request writes an HMAC-signed record to the NGARi sovereignty meter: model, timestamp, device ID, mode (on-device), and token count. GET /api/keys/attestations returns your recent receipts. This is the proof that your inference ran on sovereign edge hardware and that nothing was retained.

What this API is not

It is a capped beta on a single edge device — no SLA. It is not air-gapped end-to-end (traffic transits Cloudflare), it is not end-to-end encrypted, and it cannot claim "your data never touches our servers" (inference runs here). What it does guarantee, contractually and architecturally: zero retention of prompts and responses, and verifiable receipts. For true on-premise sovereignty, the model ships on the NGARi ONE.

Acceptable use

No unlawful activity, no resale of raw inference as a competing service, no reverse-engineering of the model. See the Terms.

Related