This guide uses source checks from Sep 12, 2026. Provider and gateway prices can change; preserve the checked date with every forecast.
Why This Topic Matters Now
The Sep 11 keyword report is a quiet but useful signal: Tier 1 searchers are still asking for `aiwave.live`, `site:aiwave.live`, `aiwaveblog`, and `aiwave api`. Those are not broad awareness searches. They look like evaluator searches from someone trying to understand whether AIWave has a real public footprint, a usable API path, and enough evidence to justify a small trial.
A blog article for that cluster should not behave like a landing page. It should behave like an evidence map. The goal is to connect the blog archive, docs, pricing JSON, status page, model catalog, trust page, and one placeholder-code request into a path a buyer can preserve. The page should also make clear what is known today, what is source-dated, and what must be rechecked before a forecast.
Source Facts Checked Today
AIWave /api/pricing checked on Sep 12, 2026 returned success=true, 64 model rows, pricing_version a42d372ccf0b5dd13ecf71203521f9d2, auto_groups=['default'], group_ratio default=3 and vip=1, and public rows enabled for default, vip, and svip groups. Computed base examples per 1M text-token units were DeepSeek V4 Flash at $0.638 input, $0.020288 cache-hit input, and $1.914 output; DeepSeek V4 Pro at $1.914 input, $0.063736 cache-hit input, and $5.742 output; DeepSeek V3.2 at $0.154 input and $0.308 output; GLM-5.1 at $2.10 input, $0.680001 cache-hit input, and $6.60 output; GLM-5 at $1.55 input, $0.400001 cache-hit input, and $4.96 output; Kimi K3 at $4.50 input, $0.90 cache-hit input, and $22.50 output; and Kimi K2.7 Code at $1.89 input, $0.285001 cache-hit input, and $6.00 output. Actual invoices still depend on account group, final route, request usage, and the receipt captured for that run.
The Sep 11 keyword report says the immediate CTR cleanup cluster is `aiwave.live`, `site:aiwave.live`, `aiwave`, `aiwaveblog`, and `aiwave api`, with Tier 1 impressions materially higher than Tier 2. The same report warns that blacklist-heavy queries should not drive topic selection.
AIWave current-state decisions keep public content focused on capability evidence: one USD billing surface, dated prices, OpenAI-compatible request shape, model catalog, current status probes, route receipts, and trust boundaries. Public articles should not expose private operating metrics or imply external submissions that have not happened.
Planning Matrix
A source-dated planning matrix keeps the page useful for engineers and procurement reviewers. It turns a search query into an auditable route decision instead of a loose model preference.
| Search intent | Evaluator question | Evidence destination |
|---|---|---|
| aiwave.live | Is this the official API surface? | Home, docs, pricing, and status |
| site:aiwave.live | Which pages are indexable? | Blog archive, docs, pricing JSON, sitemap |
| aiwaveblog | Are there technical field notes? | Blog archive plus dated article pages |
| aiwave api | Can my OpenAI client work? | Chat Completions docs and placeholder code |
| aiwave docs | Where are model names listed? | Models docs and live pricing rows |
| brand review | What proof can procurement keep? | Trust page, source dates, receipts |
Implementation Pattern
The implementation pattern keeps credentials as placeholders, pins the AIWave base URL, records the model, and leaves room for route-specific controls. Production applications should move credentials into environment or secret storage.
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY_HERE", base_url="https://aiwave.live/v1")
def evaluator_probe():
models = client.models.list()
return {
"base_url": "https://aiwave.live/v1",
"api_key": "YOUR_API_KEY_HERE",
"pricing_checked_at": "2026-09-12",
"pricing_version": "a42d372ccf0b5dd13ecf71203521f9d2",
"sample_model_ids": [getattr(item, "id", "") for item in models.data[:5]],
}
Start With the Public Evidence Path
An evaluator should be able to move from search result to evidence in a few clicks: blog archive, docs index, model docs, pricing, status, trust, and one API example. Each step answers a different concern. The blog shows technical maintenance. Docs show request shape. Pricing shows dated rows. Status shows current probes. Trust describes boundaries. The code sample proves the endpoint shape without exposing a reusable key.
Make the Blog Archive Do Real Work
The blog archive should help technical buyers scan by model family and operational problem, not only by title. Article cards should use the exact nouns buyers search for: AIWave API, docs, model catalog, pricing JSON, route receipts, streaming, DeepSeek, GLM, Kimi, and Qwen. That improves the chance that a brand query lands on a page that answers an engineering question instead of forcing a return to search.
Keep Pricing Source-Dated
The live AIWave pricing endpoint was checked on Sep 12, 2026 and returned 64 model rows. That is useful, but it is still a snapshot. A buyer should store source URL, checked date, pricing_version, account group, model name, token unit, and usage receipt. A monthly forecast should not rely on a remembered price from a previous article when a live endpoint exists.
Use Status as a Current Probe
The status page is a current operational probe, not a substitute for a buyer's monitoring window. It belongs in the evidence path because it helps an evaluator see whether public endpoints are reachable at trial time. It should not be overread as a historical availability guarantee. Teams with production risk should run their own checks and preserve timestamps beside route receipts.
Write Snippets for Verification
The best snippet copy for this cluster is narrow and verifiable: OpenAI-compatible API docs, dated pricing JSON, model catalog, current status, and route receipts. Avoid vague superlatives. A searcher using `site:aiwave.live` wants proof that pages are reachable and coherent. A searcher using `aiwaveblog` wants a technical archive, not a promotional claim.
Internal Links for Evaluators
This page should link to Blog, Docs, Models docs, Pricing, Pricing JSON, Status, and Trust. Older brand and docs articles can link back here when they mention search-result cleanup.
Procurement Review
Procurement should ask for the public URL used, checked date, route name, pricing_version, account group, usage fields, data boundary, and support path. If the evidence came from a blog article, the reviewer should still re-open the live pricing endpoint before approving a budget. The article is the map; the current endpoint is the source for the current row.
Final Checklist
The AIWave brand-search path is ready when blog, docs, pricing, status, trust, sitemap, and article pages are all linked; code samples use obvious placeholders; JSON-LD is present; source dates are visible; and private operating metrics remain out of public copy. The next content review should watch CTR movement for `aiwaveblog` and `site:aiwave.live`.