#openrouter

A provider census of open-weight model hosting. The same model name arrives at different quantizations and context limits, with wide price and speed spreads.

OpenRouter documents what its rankings count and what they exclude. A source-pinned inventory of what a usage chart measures, and what it cannot tell you.

Z.ai named its stealth model on August 26 and shipped MIT weights the same day. What the identity actually changes for an endpoint already in production.

A reveal is not reassurance — it starts a re-verification job. The checks that only become possible, or only become urgent, the day anonymity ends.

Twenty-five floating aliases across five vendor surfaces and 92 dated 2026 model-ID retirements, with notice periods computed from each vendor's own dates.

A dated census of 14 OpenRouter stealth listings since 2025: seven officially revealed, four reported only, two unresolved, and Ox Alpha still open.

A free, anonymous 1M-context reasoning model appeared on OpenRouter on August 20. Nobody has claimed it, and its no-training promise is a one-off exception.

OpenRouter's ~z-ai/glm-latest is a permanent floating router. It currently resolves to GLM-5.3 and will silently repoint when Z.ai ships its next model.

A catalog row can show a real, live price that is a time-boxed promotion, a surface-specific rate, or a listing date that is not a launch date at all.

On August 12, DeepSeek's pricing page listed V4-Pro-0813 with no changelog entry and a homepage saying nothing had changed. GA was announced a day later.

GPT-5.6 Luna fell 80% and Terra 20% on July 30. Sonnet 5's scheduled $3/$15 increase was cancelled. OpenRouter list prices mix standard with batch rates.

Qwen3.7 Flash listed at $0.03 per million input tokens on its base tier, 1M context and video input — but no published benchmarks. Where it fits in subagents.

OpenRouter added 10 frontier and open-weight models in 22 days, prices spanning ~83x on input and ~250x on output. The July 2026 releases worth routing to.

Where should you buy GLM-5.2 tokens? Z.ai lists $1.40 in / $4.40 out per Mtok, but 20+ hosts undercut it. A July 2026 price and output-cap comparison guide.

Route each request to the cheapest model that can handle it. Model routing cuts real LLM bills 40-85% with no visible quality loss. The 2026 engineering guide.

OpenRouter added five models in ten days, from Opus 4.8 to MiniMax M3 at $0.30/M input. June 2026 pricing, context windows, and usage rankings.

The LLM gateway is now critical AI infrastructure. Compare LiteLLM, Portkey, Cloudflare, Vercel, and OpenRouter on caching, routing, and build-vs-buy economics.

2026 benchmark comparison of OpenClaw, Hermes Agent, and Codex CLI. OpenRouter token data, real performance numbers, and the decision matrix.

Alibaba Qwen 3.6 Plus complete guide. 1M token context, 65K output, always-on chain-of-thought reasoning, native function calling, and #5 on OpenRouter.

OpenRouter Fusion sends queries to multiple AI models, analyzes outputs, and fuses optimal results. Deep Research agents preferred Fusion to their own outputs.

Deploy GLM 4.6 with current Z.ai, OpenRouter, vLLM, and SGLang guidance covering endpoints, pricing, MIT licensing, model IDs, and production caveats.