Show HN: ModelPlane, one OpenAI-compatible gateway for AI models

Aug 5, 2026 · 8:37 AM UTC ·1 min read · 0 reactions · 0 comments · 4 views

via

Modelplane

#ai #api #cloud #billing #opensource

TL;DR · WeSearch summary

ModelPlane is an OpenAI‑compatible gateway that consolidates access to multiple AI model providers behind a single API endpoint. It offers features such as model groups, weighted routing, fallback handling, and unified usage‑based billing. The service includes a free tier with the first 1 million tokens and tiered pricing for startups and larger teams.

Key facts

▪ModelPlane supports providers like OpenAI, Anthropic, DeepSeek, OpenRouter, Gemini, and custom OpenAI‑compatible services.
▪Users can define routing policies that include weighted load‑balancing, fallbacks, and conditional routing based on request metadata.
▪The platform tracks token usage and spend per model group, key, and customer tier in a single console.
▪A free plan provides 1 million tokens without requiring a credit card, with paid plans charging $0.02 per million tokens.
▪Pricing tiers include a startup plan at $20 per month with included credit and a free plan with no monthly fee.

How this story was covered

2 outlets in our directory ran this story, first to last over 17 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.

Centre · 1

▪ Show HN: XTokenChecker – Verifies model identities of your AI gateway — XTokenChecker

About this source

Hacker News (AI / LLM) files mainly under ai. We currently carry 3,809 of its stories.

All Hacker News (AI / LLM) coverage →

Original article

Modelplane

Read full at Modelplane →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.

Record

Original publisher	Modelplane
Canonical URL	https://modelplane.dev/
Publication time	Wed, 05 Aug 2026 08:37:28 +0000
Retrieval time	2026-08-05T08:40:41.714Z
Last seen	2026-08-05T08:40:41.714Z
Headline source	Publisher (no WeSearch rewrite)
Excerpt source	publisher body
Excerpt method	First ~120 words (~800 chars) of extracted publisher body, fair-use limited.
Summary	WeSearch · cerebras-chat (WeSearch summarizer)
Summary source text	contentText
Citation coverage	Summary is a WeSearch-generated derivative; primary citation is the original publisher URL.
Cluster	iYU6Z8DZKOQs · 2 stories
Cluster logic	Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison.
Ranking reason	Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking.
Publisher visit	Yes — open original
Substitutes article?	No — link-out required for full text

Rights status (four layers)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

WeSearch handling by dimension

Indexing	May the item be indexed (stored, ranked, made findable)?	Allowed
Snippet	May a short excerpt of the publisher's text be shown?	Allowed
AI summary	May WeSearch generate its own short summary of the article?	Limited
Retrieval / RAG	May the content be exposed for third-party retrieval-augmented generation?	Not asserted
Model training	May the content be used to train AI models?	Not asserted
Commercial reuse	May the content be reused commercially?	Not permitted

Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

ModelPlane · One AI GatewayEvery model.One endpoint.Route across OpenAI, Anthropic, DeepSeek and more behind a single API. Model groups, fallback routing, and usage billing - built in.Start freeNo credit card · First 1M tokens freeexample.pyfrom openai import OpenAIclient = OpenAI(base_url="https://modelplane.dev/v1",api_key="sk-mp-...")resp = client.chat.completions.create(model="prod-chat", # a model groupmessages=[…])→ routed to anthropic/claude, fell back OKONE API FOROpenAIAnthropicGeminiDeepSeekOpenRouterNovita AIMinimaxZ.AISee all →Six primitives. One gateway.Each works on its own.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at Modelplane.

Anonymous · no account needed

Discussion

0 comments