starveri.net is hosted on Cloudflare. It measures traffic with Cloudflare Web Analytics.
| Technology | Version | First seen |
|---|---|---|
| Frontend Build Tools & CSS1 | ||
| – | 9 Nov 2026 | |
| CDN & Hosting1 | ||
| – | 9 Nov 2026 | |
| Analytics & Tag Management1 | ||
| – | 9 Nov 2026 | |
| Fonts & Icon Fonts1 | ||
| 1.24.0 | 9 Nov 2026 | |
| Security, WAF & Bot Protection2 | ||
| – | 9 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
route1.mx.cloudflare.netroute2.mx.cloudflare.netroute3.mx.cloudflare.netchris.ns.cloudflare.comlila.ns.cloudflare.comv=spf1 include:_spf.mx.cloudflare.net ~allv=DMARC1; p=reject;# Starveri API OpenAI-compatible GPT, Codex, and dedicated Gemma Responses and Chat Completions API with public model discovery, prepaid credits, bounded code tools, and document-based credit pricing. Gemma input-token caching is unavailable. ## Primary URLs - Documentation: https://api.starveri.net/docs - OpenAPI: https://api.starveri.net/openapi.yaml - OpenAPI JSON: https://api.starveri.net/openapi.json - APIs.json: https://api.starveri.net/apis.json - Credits and keys: https://api.starveri.net/credits - Public models: https://api.starveri.net/models - Base URL: https://api.starveri.net ## Key Endpoints - GET /models - public canonical model IDs, credit price metadata, and non-billable global model spec metadata. - GET /v1/models - authenticated model discovery for API clients. - POST /v1/chat/completions - OpenAI-compatible chat completions. - POST /v1/responses - OpenAI-compatible Responses API with typed streaming events. - POST /v1/images/generations - moderated image generation on the GPT-5.6 Luna backend; accepts a text prompt, n=1..10, and protected reference file IDs. Billing is 0.5 credits per successful output image plus prompt and reference image inputs at GPT-5.6 Luna input pricing; input cost varies with the request, so totals are not fixed. - POST /v1/demo/chat - free GPT 5.5 no-reasoning text demo with moderation, five requests, 2,000 demo tokens, IP-based limits, no files, no images, and one concurrent request. ## Model Families - GPT 5.6 Sol - GPT 6 Astra (Standard inference; max reasoning; no Flex) - GPT 6 Sol (`gpt-6-sol`; paid Tiers 1–5; Standard and Pro; low through max reasoning; no Flex) - GPT 6.1 Terra (`gpt-6.1-terra`; paid Tiers 1–5; Standard service, Pro Standard pricing; none through max reasoning) - GPT 6 Luna (`gpt-6-luna`; Free and paid Tiers 1–5; Standard and Pro; low through max reasoning; no Flex) - GPT 5.6 Terra - GPT 5.6 Luna - GPT 5.5 - Gemma 4 (dedicated serving runtime; Standard only; automatic moderation; thinking on/off; no reasoning fields) - Gemma 4 Uncensored (dedicated serving runtime; Standard only; no automatic content moderation; thinking on/off; no reasoning fields) ## Service profiles - Public inference currently exposes Standard service, plus Flex where /models advertises it. Higher access profiles remain model-specific. - Long-context pricing remains the existing 2× model-token multiplier above 30% of a model context window. Separately priced tools are unchanged. Use /models as the public source of truth for current canonical model IDs, context limits, pricing metadata, and non-billable global model spec metadata. ## Search-Intent Pages - OpenRouter alternative for GPT/Codex API credits: https://api.starveri.net/openrouter-alternative
Contact: https://api.starveri.net/privacy Policy: https://api.starveri.net/privacy Preferred-Languages: en Expires: 2026-12-31T23:59:59Z
| – |
| 9 Nov 2026 |