# LLM Pricing (remote · llm-pricing-api.fly.dev)

Real-time, drift-verified LLM pricing across 26 providers with cost+quality model routing.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `llm-pricing-api.fly.dev`: 61/100 (this document), [markdown](https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api.md), [page](https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api)

## Channel facts

- Endpoint: `https://llm-pricing-api.fly.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.73.2`

## 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 2026-10-22.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 29 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3677 tokens (~126/item across 29 items; 29 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_price_alert" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the LLM Pricing MCP server?

LLM Pricing is a hosted endpoint at https://llm-pricing-api.fly.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http skakumanu-llm-pricing-mcp-server 'https://llm-pricing-api.fly.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "skakumanu-llm-pricing-mcp-server": {
      "url": "https://llm-pricing-api.fly.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "skakumanu-llm-pricing-mcp-server": {
      "type": "http",
      "url": "https://llm-pricing-api.fly.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.skakumanu-llm-pricing-mcp-server]
url = "https://llm-pricing-api.fly.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "skakumanu-llm-pricing-mcp-server": {
      "type": "remote",
      "url": "https://llm-pricing-api.fly.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add skakumanu-llm-pricing-mcp-server --url 'https://llm-pricing-api.fly.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  skakumanu-llm-pricing-mcp-server:
    url: "https://llm-pricing-api.fly.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "skakumanu-llm-pricing-mcp-server": {
      "Transport": "http",
      "Url": "https://llm-pricing-api.fly.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add skakumanu-llm-pricing-mcp-server -t streamable-http -u 'https://llm-pricing-api.fly.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "skakumanu-llm-pricing-mcp-server": {
      "type": "http",
      "url": "https://llm-pricing-api.fly.dev/mcp"
    }
  }
}
```

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.

### 2026-10-22 (score 61, +1)

- [functional] Server version: 1.73.3 → 1.73.4

### 2026-10-21 (score 60, 0)

- [functional] Server version: 1.73.2 → 1.73.3

### 2026-10-20 (score 60, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-19 (score 59)

First indexed and scored.

## MCP tools (29)

### `get_all_pricing` (~22 tokens)

Get current pricing for all LLM models from all providers

### `estimate_cost` (~74 tokens)

Estimate the cost of using a specific LLM model

Input parameters:

- `input_tokens` (integer, required): Number of input tokens
- `model_name` (string, required): Name of the LLM model (e.g., 'gpt-4', 'claude-3-opus')
- `output_tokens` (integer, required): Number of output tokens

### `compare_costs` (~55 tokens)

Compare costs for multiple LLM models

Input parameters:

- `input_tokens` (integer, required): Number of input tokens
- `model_names` (array, required): List of model names to compare
- `output_tokens` (integer, required): Number of output tokens

### `get_performance_metrics` (~63 tokens)

Get performance metrics (throughput, latency, context window) for models

Input parameters:

- `include_cost` (boolean): Include cost metrics in response (default: true)
- `provider` (string): Optional provider filter (e.g., 'openai', 'anthropic')

### `get_use_cases` (~30 tokens)

Get recommended use cases and strengths for LLM models

Input parameters:

- `provider` (string): Optional provider filter

### `get_telemetry` (~64 tokens)

Get MCP server telemetry and usage statistics including tool usage, response times, and error rates

Input parameters:

- `include_details` (boolean): Include detailed statistics (default: true)
- `limit` (integer): Maximum items per category (default: 10, max: 50)

### `get_pricing_history` (~142 tokens)

Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given number of days.

Input parameters:

- `days` (integer): Look-back window in days (default: 30, max: 365)
- `limit` (integer): Maximum number of snapshot rows to return (default: 50, max: 500)
- `model_name` (string): Filter by model name (e.g. 'gpt-4o'). Omit for all models.
- `provider` (string): Filter by provider (e.g. 'openai'). Omit for all providers.

### `get_pricing_trends` (~114 tokens)

Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'decreased', or 'unchanged'). Use this to answer questions like 'which models got cheaper this month?' or 'which providers raised prices recently?'

Input parameters:

- `days` (integer): Look-back window in days (default: 30, max: 365)
- `limit` (integer): Maximum models to return (default: 20, max: 100)

### `register_price_alert` (~130 tokens)

Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provider or model. Returns the alert ID.

Input parameters:

- `model_name` (string): Limit to a specific model name. Omit for all models.
- `provider` (string): Limit to a specific provider (e.g. 'openai'). Omit for all.
- `threshold_pct` (number): Minimum absolute % price change to trigger the alert (default: 5.0)
- `url` (string, required): Webhook URL to POST when the alert fires

### `list_price_alerts` (~23 tokens)

List all registered price-change webhook alerts with their IDs and settings.

### `delete_price_alert` (~44 tokens)

Delete a registered price-change alert by its ID.

Input parameters:

- `alert_id` (integer, required): The ID of the alert to delete (from list_price_alerts or register_price_alert)

### `get_pricing_export_url` (~153 tokens)

Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) or JSON (for code). Use this when the user asks to export, download, or save pricing data.

Input parameters:

- `days` (integer): Look-back window in days (default: 30, max: 365)
- `format` (string): Output format: 'csv' (default) or 'json'
- `limit` (integer): Max rows to export (default: 10000, max: 100000)
- `model_name` (string): Filter by model name (optional)
- `provider` (string): Filter by provider (optional)

### `list_conversations` (~74 tokens)

List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user asks to see their past conversations or chat history.

Input parameters:

- `limit` (integer): Maximum number of conversations to return (default: 20, max: 100)

### `delete_conversation` (~60 tokens)

Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the conversation ID.

Input parameters:

- `conversation_id` (string, required): The ID of the conversation to delete

### `get_ide_pricing` (~186 tokens)

Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly subscription cost, inline completion support, context window, and per-tool strengths. Use this when the user asks to compare IDE AI tools, subscription-based coding assistants, or wants to know which IDE AI fits their budget.

Input parameters:

- `inline_only` (boolean): If true, only return tools that support real-time inline code completion
- `max_monthly` (number): Only return plans at or below this monthly USD price (e.g. 20 for $20/mo)
- `provider` (string): Filter by provider name (partial match, case-insensitive). Examples: 'GitHub Copilot', 'Cursor', 'Windsurf', 'JetBrains', 'Amazon Q', 'Tabnine'

### `predict_cost` (~311 tokens)

Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or accepts one explicitly), estimates output length from empirical I/O profiles, and returns all models ranked cheapest-first with effective cost after prompt-cache savings. Also surfaces the best quality-per-dollar pick. Use this before making any LLM API call to avoid surprise bills.

Input parameters:

- `cache_hit_ratio` (number): Fraction of calls that hit the prompt cache (0–1). Set this if you have a large reusable system prompt. Supported providers: Anthropic (10% cache rate), OpenAI (50%), Google (25%). Default: 0
- `min_context_tokens` (integer): Minimum context window size required in tokens (optional)
- `prompt` (string, required): The actual prompt text to cost-estimate (required)
- `require_function_calling` (boolean): Only include models that support function/tool calling (default: false)
- `require_vision` (boolean): Only include models that support image/vision input (default: false)
- `task_type` (string): Task type for output-length estimation. Auto-inferred from prompt if omitted. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasoning…
- `top_n` (integer): Number of models to return, ranked cheapest-first (default: 10, max: 50)

### `optimize_workload` (~188 tokens)

Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of workloads (task type + monthly volume + optional quality floor and capability requirements) and returns a per-task model allocation, the total monthly cost, and the saving versus the best single-model deployment. If a monthly budget is given, leftover headroom is spent on the most cost-efficient quality upgrades. Use when the user asks how to cut LLM spend across several task types, or whether tiered model routing is worth it.

Input parameters:

- `min_quality_score` (number): Global quality floor (0-100) applied to every workload
- `monthly_budget_usd` (number): Total monthly budget in USD. Leftover headroom is spent on the most cost-efficient quality upgrades.
- `workloads` (array, required): One entry per task type in the workload mix

### `recommend_model` (~473 tokens)

Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies the description into a task type, then runs it through the same routing engine behind /router/recommend (live pricing + benchmark quality, hard filters for cost/quality/context window, scored by quality-per-dollar). Returns the best match plus up to 3 alternatives. Read-only — use predict_cost first if you also want per-model cost estimates for an actual prompt, and optimize_workload if you have several distinct task types to route at once.

Input parameters:

- `avg_input_tokens` (integer): Average input tokens per request (default: 500)
- `avg_output_tokens` (integer): Average output tokens per request (default: 200)
- `description` (string, required): Free-text description of the use case, e.g. 'summarize long customer support tickets' or 'generate Python unit tests'
- `estimated_monthly_requests` (integer): Estimated requests per month (default: 1000)
- `exclude_reasoning_models` (boolean): Exclude slow thinking/reasoning models (default: false)
- `ide_context` (string): IDE context hint — boosts IDE-native tools: 'copilot' | 'cursor' | 'windsurf' | 'claude_code' | 'jetbrains' | 'amazon_q'
- `max_cost_per_1m_tokens` (number): Maximum acceptable average cost per 1M tokens (USD)
- `min_context_window` (integer): Minimum required context window size (tokens)
- `min_quality_score` (number): Minimum required quality score (0-100)
- `monthly_budget_usd` (number): Monthly spend ceiling in USD. Combined with estimated_monthly_requests, avg_input_tokens, and avg_output_tokens to hard-filter models that would exceed it.
- `prefer_low_latency` (boolean): Prioritise lower-latency models (default: false)
- `preferred_provider` (string): Preferred provider name (10% score boost applied)
- `task_type` (string): Optional explicit task type, bypassing auto-classification of the description. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasonin…

### `check_price_drift` (~167 tokens)

Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with the registry by more than the threshold is automatically withheld from serving the moment it's detected, not just when this tool runs. This reports what's currently withheld and why. The price value itself is never overwritten by the registry. Use when the user asks whether the pricing data is accurate or up to date, or wants to audit a specific provider's rates.

Input parameters:

- `limit` (integer): Maximum findings to return (default: 50, max: 200)
- `provider` (string): Limit the audit to one provider (partial, case-insensitive)
- `threshold_pct` (number): Minimum % difference to report (default: 5)

### `get_data_quality` (~94 tokens)

Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to price drift, how many are newly discovered and not yet priced, and how many confirmed prices are over 90 days old. A single trust signal, distinct from check_price_drift which lists individual disputes. Use when the user asks how accurate or trustworthy the pricing data is, overall.

### `get_cache_stats` (~82 tokens)

Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /router/recommend (never combined). Server-operations introspection for confirming the cache is reducing recomputation in production, not a pricing question. Counts reset on process restart; reading them never changes them.

### `record_usage` (~247 tokens)

Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend' counterpart to estimate_cost's hypothetical numbers. Optionally scope to an org_id for per-org spend tracking. Resubmitting the same request_id for the same org is a no-op. Use when the user wants to log or track real LLM spend, not just estimate it.

Input parameters:

- `input_tokens` (integer, required): Number of input tokens actually used
- `model_name` (string, required): Name of the LLM model that was called
- `occurred_at` (number): Unix timestamp when the call happened (default: now)
- `org_id` (string): Optional organisation ID to attribute this usage to
- `output_tokens` (integer, required): Number of output tokens actually used
- `request_id` (string): Optional idempotency key — resubmitting the same value is a no-op
- `session_id` (string): Optional session ID to tag this event with, so it can later be grouped and retrieved via analyze_session_usage — e.g. a bounded burst of calls like a coding-agent run or a chat session

### `get_usage_summary` (~94 tokens)

Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usage. Use when the user asks what they've actually spent, as opposed to a hypothetical cost estimate.

Input parameters:

- `days` (integer): Look-back window in days (default: 30, max: 365)
- `org_id` (string): Optional organisation ID filter

### `analyze_session_usage` (~183 tokens)

Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a per-model breakdown if more than one model was used. Also runs the session's own observed token pattern through the same routing engine behind recommend_model / POST /router/recommend to produce a grounded recommendation — or confirm the current choice is already optimal — with the estimated dollar savings or increase versus this session's actual cost. Returns has_data: false with no recommendation if the session_id has no recorded usage. Advisory only — never switches or reroutes anything.

Input parameters:

- `org_id` (string): Optional organisation ID filter — scopes the lookup to usage events recorded under that org_id, same as get_usage_summary's org_id
- `session_id` (string, required): The session_id previously used when calling record_usage

### `import_session_usage` (~296 tokens)

Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a calling agent (e.g. VS Code Copilot Chat) already has a session's turn-by-turn history in its own local store and wants this server to report on it exactly as if it had been tracked live. Accepts a list of entries under one shared session_id; each entry resolves its input and output tokens independently, either from exact counts when known or by estimating from raw turn text using this server's existing token counter. Cost is always computed server-side from current pricing, never trusted from the caller. A malformed entry (no usable tokens/text on one side, or an unresolvable model_name) is reported as its own per-entry failure and does not fail the rest of the batch. Idempotent like record_usage — resubmitting the same entries (same request_id, or the same session_id/model/occurred_at/token-or-text when request_id is omitted) is a no-op. Recorded usage is then readable via analyze_session_usage and GET /usage/session/{session_id}.

Input parameters:

- `entries` (array, required): Usage entries to import, one per turn/call in the session
- `org_id` (string): Optional organisation ID to attribute this usage to
- `session_id` (string, required): Shared session ID to tag every entry in this batch with

### `register_budget_alert` (~148 tokens)

Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope to a specific org_id (omit for total spend across all orgs). Fires at most once per period_days while spend stays over threshold. Returns the alert ID.

Input parameters:

- `org_id` (string): Organisation to monitor. Omit for total spend across all orgs.
- `period_days` (integer): Rolling look-back window for the spend check, in days (default: 30)
- `threshold_usd` (number, required): Spend level in USD that triggers the alert
- `url` (string, required): Webhook URL to POST when the alert fires

### `list_budget_alerts` (~24 tokens)

List all registered budget-spend webhook alerts with their IDs and settings.

### `delete_budget_alert` (~45 tokens)

Delete a registered budget-spend alert by its ID.

Input parameters:

- `alert_id` (integer, required): The ID of the alert to delete (from list_budget_alerts or register_budget_alert)

### `ask_agent` (~91 tokens)

Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything that benefits from multi-step reasoning.

Input parameters:

- `autonomous` (boolean): Run in autonomous task mode (default: false)
- `conversation_id` (string): Optional conversation ID to continue a previous session
- `message` (string, required): The question or task for the pricing agent

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api#diagnostics

## Score history

- 2026-10-22: 61
- 2026-10-21: 60
- 2026-10-20: 60
- 2026-10-19: 59

## Common questions

### What is the LLM Pricing MCP server?

LLM Pricing is an MCP server listed in the public MCP registry as io.github.skakumanu/llm-pricing-mcp-server. Real-time, drift-verified LLM pricing across 26 providers with cost+quality model routing. This page covers its hosted endpoint (https://llm-pricing-api.fly.dev/mcp).

### Is the LLM Pricing MCP server safe to use?

LLM Pricing scores 61 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the LLM Pricing MCP server expose?

LLM Pricing exposes 29 tools: get_all_pricing, estimate_cost, compare_costs, get_performance_metrics, get_use_cases, and 24 more. Their descriptions and schemas cost roughly 3,677 tokens of context every time the server is loaded.

### Does the LLM Pricing MCP server require authentication?

No. We connected to LLM Pricing without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the LLM Pricing MCP server still maintained?

LLM Pricing is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://llm-pricing-api.fly.dev/mcp
- Repository: https://github.com/skakumanu/llm-pricing-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api.xml
- Changelog JSON feed: https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api.json
- HTML version of this page: https://verifymcp.io/servers/skakumanu-llm-pricing-mcp-server/llm-pricing-api