AI Wave

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AI Wave": {
      "url": "https://aiwave.elopstudio.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (8)

• list_model_changes

  Changes across AI models: new releases, price changes, API changes and deprecations. Normalized from vendor release notes, Hugging Face, the OpenRouter catalog, GitHub and the LiteLLM price map, deduplicated per model, each marked official or pending review. Poll with `since` (unix seconds) and feed the returned `latest` back next time.

  Parameters:

  • type — string
  • limit — number — 1-100, default 20
  • model — string — Vendor slug, e.g. claude
  • since — number — Unix seconds. Only changes detected after this, oldest first.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_model

  Pricing, context length and catalog status for one model. Accepts an OpenRouter id (anthropic/claude-opus-5) or a Hugging Face repo id.

  Parameters:

  • id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_price_history

  Price history for one model: when the price changed and to what. The public catalog only exposes the current price, so this answers 'was this cheaper last month?'. Each entry holds until the next one. History starts when AI Wave began recording, not when the model launched.

  Parameters:

  • id (required) — string — OpenRouter id or Hugging Face repo id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_models

  Shortlist models by budget, context and capability, ranked by measured performance. Use this to answer 'which model should I use for X': it returns benchmark scores alongside price so the trade-off is visible in one call. Sort by a subject (math, coding, science, reading) to find a model good at one thing.

  Parameters:

  • mode — string — What the model does. Non-chat modes are priced in other units: check price.unit.
  • limit — number — 1-50, default 10
  • sortBy — string — Ranking basis. Default 'intelligence' (overall). 'buzz' is popularity, not skill.
  • vendor — string — OpenRouter namespace, e.g. anthropic
  • accepts — string — What the model must be able to take in, e.g. image for vision tasks.
  • outputs — string — What the model produces. A model that accepts video but writes text is 'text', not 'video': filter on what you need made, not what it can read.
  • minContext — number
  • maxInputPrice — number — USD per 1M input tokens
  • minIntelligence — number — Lowest acceptable overall index. Leaders sit near 53; the median is 16.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_models

  Put two or more models side by side: price, context, benchmark scores per subject, and what each costs per month at a given volume. Use this instead of calling get_model repeatedly: it aligns the fields and marks which subjects a model has not been tested on, so a missing score is not read as a low one.

  Parameters:

  • ids (required) — array — 2-6 OpenRouter ids, e.g. ['anthropic/claude-opus-5','openai/gpt-5.2']
  • monthlyMillionTokens — number — Volume for the cost estimate. Default 10 (10M tokens a month).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• estimate_cost

  What one model costs per month at a given token volume, in USD and KRW. Token prices are per million and hard to reason about directly; this turns them into a monthly bill. Input and output are mixed 75/25 unless you pass your own split.

  Parameters:

  • id (required) — string — OpenRouter id or Hugging Face repo id
  • inputShare — number — 0-1, share of tokens that are input. Default 0.75
  • monthlyMillionTokens — number — Default 10

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_today

  Today in one call: the top 5 models, which ones climbed, whose pricing changed in the last 24h, and what was newly listed in the last 7 days. Use this instead of paging list_model_changes and re-deriving the summary: price changes are already collapsed to one per model, with the raw count kept.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• find_replacement

  What to switch to when a model is gone or you need a fallback. Ranked by closeness in measured performance, not by vendor or price: what you usually need to preserve first is the quality of the output. Candidates whose context window is less than half the original are excluded. Returns the score, price and context deltas so you can judge; we do not pick for you.

  Parameters:

  • id (required) — string — OpenRouter id or Hugging Face repo id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.