Inference API for open-weight models

OpenAI-compatible API priced per million tokens; this page links and shows every public surface of the offering. We work with routers, marketplaces and direct customers.

Surfaces

APIlive

https://api.netrasystems.ai/

Run a live demo request, see the settled bill, track your key's usage and receipts.

Open the API

TCO & cost transparency

https://tco.netrasystems.ai/

List pricing against public hardware cost basis, with a break-even calculator.

Open the TCO page

Grafana

https://grafana.netrasystems.ai/

Operational dashboards for the serving fleet (login required).

Open Grafana

Docs

https://docs.netrasystems.ai/

API reference and integration documentation.

Open the docs

Status & health

https://api.netrasystems.ai/healthz

Public liveness (/healthz) and readiness (/readyz) JSON endpoints for monitoring.

Open /healthz

Models and pricing

Model	Context	Input	Cached input	Output
Qwen3.8 27B	131,072	$0.20	$0.05	$0.80

USD per 1M tokens. Usage is billed on the token counts returned in each response's usage object.

Quickstart

OpenAI-compatible /v1/chat/completions and /v1/models
Streaming (SSE), tool and function calling
Prompt caching: cached input tokens are reported in usage.prompt_tokens_details.cached_tokens and billed at the cached rate
Per-key rate limits, with a Retry-After header on 429 responses

curl https://api.netrasystems.ai/v1/chat/completions \
  -H "Authorization: Bearer $NETRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.8-27b","messages":[{"role":"user","content":"Hello"}]}'

We issue endpoints and keys during onboarding.

Cost transparency

The embedded page below is the live tco.netrasystems.ai site.

Open the TCO page if the frame is blocked.

Infrastructure

We serve on NVIDIA and AMD hardware with our in-house serving engine.

Data policy

We do not train on customer prompts or completions.
We do not store prompts or completions beyond short-lived prompt caching.
We keep request metadata (timestamp, model, token counts, latency, status) for billing, abuse prevention and reliability.

For routers and marketplaces

We provide dedicated keys, usage reporting per key and an operational contact. To list Netra as a provider, email us.

Contact

[email protected]