# OptimToken (remote · ai-pricing-hub-mcp-9604f763.alpic.live)

Compare LLM API pricing, estimate workload costs, and benchmark cloud compute. By OptimNow.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-17

## Components

- remote · `ai-pricing-hub-mcp-9604f763.alpic.live`: 70/100 (this document), [markdown](https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763.md), [page](https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763)

## Channel facts

- Endpoint: `https://ai-pricing-hub-mcp-9604f763.alpic.live/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-17.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 956 tokens (~106/item across 9 items; 3 tools + 6 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 3 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add --transport http optimnow-ai-pricing-hub https://ai-pricing-hub-mcp-9604f763.alpic.live/
```

### Codex

```toml
[mcp_servers.optimnow-ai-pricing-hub]
url = "https://ai-pricing-hub-mcp-9604f763.alpic.live/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "optimnow-ai-pricing-hub": {
      "type": "remote",
      "url": "https://ai-pricing-hub-mcp-9604f763.alpic.live/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add optimnow-ai-pricing-hub --url https://ai-pricing-hub-mcp-9604f763.alpic.live/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  optimnow-ai-pricing-hub:
    url: "https://ai-pricing-hub-mcp-9604f763.alpic.live/"
```

### Other

```json
{
  "mcpServers": {
    "optimnow-ai-pricing-hub": {
      "type": "http",
      "url": "https://ai-pricing-hub-mcp-9604f763.alpic.live/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-17 (score 70, 0)

- [security] Resource “compare-compute-pricing” now points somewhere else: ui://widgets/apps-sdk/compare-compute-pricing.html → ui://widgets/ext-apps/compare-compute-pricing.html
- [security] Resource “compare-llm-models” now points somewhere else: ui://widgets/apps-sdk/compare-llm-models.html → ui://widgets/ext-apps/compare-llm-models.html
- [security] Resource “estimate-llm-cost” now points somewhere else: ui://widgets/apps-sdk/estimate-llm-cost.html → ui://widgets/ext-apps/estimate-llm-cost.html

### 2026-08-16 (score 70, −1)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 0.1.0
- [security] Resource “compare-compute-pricing” now points somewhere else: ui://widgets/apps-sdk/compare-compute-pricing.html → ui://widgets/ext-apps/compare-compute-pricing.html
- [security] Resource “compare-llm-models” now points somewhere else: ui://widgets/apps-sdk/compare-llm-models.html → ui://widgets/ext-apps/compare-llm-models.html
- [security] Resource “estimate-llm-cost” now points somewhere else: ui://widgets/apps-sdk/estimate-llm-cost.html → ui://widgets/ext-apps/estimate-llm-cost.html
- [security] Tool “compare-compute-pricing” rewrote its description, which is the text the model reads
- [security] Tool “compare-llm-models” rewrote its description, which is the text the model reads
- [security] Tool “estimate-llm-cost” rewrote its description, which is the text the model reads
- [functional regression] “estimate-llm-cost” changed the type of “customInputTokens”: number → integer
- [functional regression] “estimate-llm-cost” changed the type of “customOutputTokens”: number → integer
- [functional regression] “estimate-llm-cost” changed the type of “monthlyVolume”: number → integer
- [functional improvement] Tool “compare-compute-pricing” now declares an output schema
- [functional improvement] Tool “compare-llm-models” now declares an output schema
- [functional improvement] Tool “estimate-llm-cost” now declares an output schema
- [functional] First check of Tool coverage: 100
- [cosmetic] “compare-llm-models” added an optional parameter “openness”
- [cosmetic] “compare-llm-models” reworded the description of “category”
- [cosmetic] “compare-llm-models” reworded the description of “useCasePreset”
- [cosmetic] “estimate-llm-cost” reworded the description of “useCasePreset”
- [cosmetic] “compare-compute-pricing” dropped the optional parameter “os”

### 2026-08-15 (score 71, 0)

- [security] Resource “compare-compute-pricing” now points somewhere else: ui://widgets/apps-sdk/compare-compute-pricing.html → ui://widgets/ext-apps/compare-compute-pricing.html
- [security] Resource “compare-llm-models” now points somewhere else: ui://widgets/apps-sdk/compare-llm-models.html → ui://widgets/ext-apps/compare-llm-models.html
- [security] Resource “estimate-llm-cost” now points somewhere else: ui://widgets/apps-sdk/estimate-llm-cost.html → ui://widgets/ext-apps/estimate-llm-cost.html
- [functional improvement] Stability: unverified → 0.03

### 2026-08-14 (score 71)

First indexed and scored.

## MCP tools (3)

### `compare-llm-models` (~375 tokens)

Compare AI/LLM models by price, quality (ELO), efficiency, and capabilities. Fetches live data from OpenRouter API. Filter by provider, price tier (category), openness, capability, price range, or minimum ELO score. Optionally enrich with business metrics for a use case. Price tier and openness are independent: a model can be Frontier-priced and open-weight at once. Reports both list-price cost and the optimized cost achievable with prompt caching and the batch API. IMPORTANT: Report all prices, costs, and scores EXACTLY as returned. Do NOT add commentary, opinions, or recommendations beyond what the data shows. Present the results as a table and let the user draw conclusions.

Input parameters:

- `capability` (string): Filter by capability: Text, Vision, Code, Reasoning, Agents, Image Gen, Audio
- `category` (string): Filter by price tier: Frontier, Mid-tier, Budget, Image
- `limit` (number): Max models to return (default: 15)
- `maxInputPrice` (number): Max input price per 1M tokens in USD
- `maxOutputPrice` (number): Max output price per 1M tokens in USD
- `minElo` (number): Minimum ELO score (quality benchmark from Chatbot Arena)
- `openness` (string): Filter by self-hostability, derived from the licence: Open source, Open weights, Proprietary, Unknown
- `provider` (string): Filter by provider name (e.g. 'OpenAI', 'Anthropic', 'Google')
- `useCasePreset` (string): Use case for cost estimation. Default: supportTicket
- `volumePreset` (string): Monthly request volume: 10k, 100k, or 1m. Default: 100k

Output parameters:

- `catalogSize` (number)
- `dataAsOf` (string)
- `eloAsOf` (string)
- `error` (string)
- `finopsBadge` (object)
- `matchingCount` (number)
- `models` (array)
- `source` (string)
- `useCaseLabel` (string)
- `volumeLabel` (string)

### `estimate-llm-cost` (~200 tokens)

Estimate per-request and monthly costs for AI/LLM models across different use cases and volumes. Provide a model name to get detailed cost breakdowns, or compare costs across all use case presets. Each figure comes twice: list price, and the optimized price achievable with prompt caching and the batch API. IMPORTANT: Report all cost figures EXACTLY as returned. Do NOT add commentary or recommendations beyond the data.

Input parameters:

- `customInputTokens` (integer): Custom input tokens per request (overrides preset)
- `customOutputTokens` (integer): Custom output tokens per request (overrides preset)
- `modelName` (string): Model name to estimate costs for (e.g. 'GPT-4o', 'Claude Sonnet 4'). If omitted, shows top models.
- `monthlyVolume` (integer): Custom monthly volume (default: 100,000)
- `useCasePreset` (string): Use case preset. Default: all presets.

Output parameters:

- `dataAsOf` (string)
- `eloAsOf` (string)
- `error` (string)
- `modelCosts` (array)
- `source` (string)
- `volume` (number)

### `compare-compute-pricing` (~301 tokens)

Compare cloud compute instance pricing across AWS, Azure, GCP, DigitalOcean, OCI, OVH, and Alibaba. Filter by provider, vCPUs, memory, category, processor, or use case. All prices are Linux on-demand list prices in USD. IMPORTANT: Report all prices EXACTLY as returned. Do NOT add commentary or recommendations beyond the data.

Input parameters:

- `category` (string): Instance category: General Purpose, Compute Optimized, Memory Optimized, Storage Optimized, GPU / Accelerated, Burstable
- `limit` (number): Max instances to return (default: 20)
- `maxMemory` (number): Maximum memory in GiB
- `maxVCPUs` (number): Maximum number of vCPUs
- `minMemory` (number): Minimum memory in GiB
- `minVCPUs` (number): Minimum number of vCPUs
- `processor` (string): Processor filter: Intel, AMD, Graviton, Ampere, NVIDIA A100, NVIDIA H100, etc.
- `provider` (string): Cloud provider: AWS, Azure, GCP, DigitalOcean, OCI, OVH, Alibaba
- `sortBy` (string): Sort by: price, vcpus, memory, pricePerVCPU. Default: price
- `useCase` (string): Use case filter: Web App, Database, HPC, ML & AI, Dev/Test, Big Data

Output parameters:

- `catalogSize` (number)
- `error` (string)
- `instances` (array)
- `matchingCount` (number)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763#diagnostics

## Score history

- 2026-08-17: 70
- 2026-08-16: 70
- 2026-08-15: 71
- 2026-08-14: 71

## Links

- Remote endpoint: https://ai-pricing-hub-mcp-9604f763.alpic.live/
- Repository: https://github.com/OptimNow/ai-pricing-hub-mcp
- Website: https://optimtoken.optimnow.io/mcp
- Changelog RSS feed: https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763.xml
- Changelog JSON feed: https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763.json
- HTML version of this page: https://verifymcp.io/servers/optimnow-ai-pricing-hub/ai-pricing-hub-mcp-9604f763