# Cheapest LLM API (remote · cheapestllmapi.com)

Compare LLM API prices, search models and providers, and access reviewed benchmark results.

- Trust score: 24/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `cheapestllmapi.com`: 24/100 (this document), [markdown](https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi.md), [page](https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi)

## Channel facts

- Endpoint: `https://cheapestllmapi.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-05.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 405.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Cheapest LLM API MCP server?

Cheapest LLM API is a hosted endpoint at https://cheapestllmapi.com/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 tehtelabs-cheapestllmapi 'https://cheapestllmapi.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tehtelabs-cheapestllmapi": {
      "url": "https://cheapestllmapi.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tehtelabs-cheapestllmapi": {
      "type": "http",
      "url": "https://cheapestllmapi.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tehtelabs-cheapestllmapi]
url = "https://cheapestllmapi.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tehtelabs-cheapestllmapi": {
      "type": "remote",
      "url": "https://cheapestllmapi.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tehtelabs-cheapestllmapi --url 'https://cheapestllmapi.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tehtelabs-cheapestllmapi:
    url: "https://cheapestllmapi.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tehtelabs-cheapestllmapi": {
      "Transport": "http",
      "Url": "https://cheapestllmapi.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tehtelabs-cheapestllmapi -t streamable-http -u 'https://cheapestllmapi.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tehtelabs-cheapestllmapi": {
      "type": "http",
      "url": "https://cheapestllmapi.com/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.

### 2026-10-23 (score 24, −51)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.60 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-22 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 74, +40)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.57
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-20 (score 34, +10)

- [security improvement] Transport: fail → pass

### 2026-10-19 (score 24, −49)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.47 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-18 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 71, −2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “execute” rewrote its description, which is the text the model reads
- [security] Tool “offer_compare” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 0% → 15%
- [functional] Schema quality: excellent → good
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “coding_agent_detail”
- [functional] New tool “coding_agent_list”
- [functional] New tool “coding_agent_releases”
- [functional] New tool “coding_agent_upgrade”
- [functional] New tool “price_watch”
- [cosmetic] “offer_compare” added an optional parameter “average_input_tokens”
- [cosmetic] “offer_compare” added an optional parameter “average_output_tokens”
- [cosmetic] “offer_compare” added an optional parameter “benchmark_id”
- [cosmetic] “offer_compare” added an optional parameter “cache_hit_percent”
- [cosmetic] “offer_compare” added an optional parameter “cache_write_percent”
- [cosmetic] “offer_compare” added an optional parameter “execution”
- [cosmetic] “offer_compare” added an optional parameter “limit”
- [cosmetic] “offer_compare” added an optional parameter “minimum_context_tokens”
- [cosmetic] “offer_compare” added an optional parameter “minimum_score”
- [cosmetic] “offer_compare” added an optional parameter “offset”
- [cosmetic] “offer_compare” added an optional parameter “open_weights”
- [cosmetic] “offer_compare” added an optional parameter “require_known_host”
- [cosmetic] “offer_compare” added an optional parameter “require_official_prices”
- [cosmetic] “offer_compare” added an optional parameter “required_capabilities”
- [cosmetic] “offer_compare” added an optional parameter “retry_percent”
- [cosmetic] “offer_compare” added an optional parameter “route_type”
- [cosmetic] “offer_compare” added an optional parameter “task”

## MCP tools (12)

### `catalog_search` (~100 tokens)

Search LLM catalog

Find canonical model slugs, context limits, and provider prices. Optional provider_slug filters availability, not the provider in bestOffer. bestOffer is selected for 10M input + 2M output tokens; use offer_compare for your workload. Follow pagination.hasMore.

Input parameters:

- `category_slug` (string)
- `page` (integer)
- `page_size` (integer)
- `provider_slug` (string)
- `query` (string)

Output parameters:

- `data` (object)
- `meta` (object)
- `pagination` (object)

### `model_detail` (~60 tokens)

Get model details

Get capabilities, context/output limits, and current sourced provider offers by model_slug from catalog_search. Prices are base-context rates; long-context tiers, cache writes, batch discounts, and free-tier quotas can change actual cost.

Input parameters:

- `model_slug` (string, required)

Output parameters:

- `data` (object)
- `meta` (object)

### `offer_compare` (~380 tokens)

Compare provider offers

Rank current chat offers for up to five canonical model slugs with the website calculator: context-tier prices, cache reads/writes, retries, supported batch rates, capability/benchmark requirements, provider/route preferences, and evidence filters. Input totals include cache shares; cache_hit_percent plus cache_write_percent must be <=100. Average request sizes determine tiers and capacity. Batch is Anthropic direct only. Unknown required evidence excludes offers; missing cache-read rates use standard input rates. Inspect costs, qualification, warnings, assumptions, excludedModels, and pagination.hasMore. Free quotas, non-token fees, and media token accounting are excluded.

Input parameters:

- `average_input_tokens` (integer)
- `average_output_tokens` (integer)
- `benchmark_id` (string)
- `cache_hit_percent` (number)
- `cache_write_percent` (number)
- `execution` (string): Batch supports Anthropic direct routes with a published 50% token discount; unsupported routes are excluded.
- `input_tokens` (integer)
- `limit` (integer)
- `minimum_context_tokens` (integer)
- `minimum_score` (number): Zero disables score qualification; a positive threshold excludes missing exact benchmark matches.
- `model_slugs` (array, required)
- `offset` (integer)
- `open_weights` (boolean)
- `output_tokens` (integer)
- `provider_slugs` (array)
- `require_known_host` (boolean): Exclude routes without a named underlying inference provider.
- `require_official_prices` (boolean): Require official paired input/output price verification. Cache rates may have different source provenance.
- `required_capabilities` (array)
- `retry_percent` (number)
- `route_type` (string)
- `task` (string): Coding requires the code capability; extraction requires structured output. Every offer must support chat.

Output parameters:

- `assumptions` (array)
- `data` (object)
- `meta` (object)
- `pagination` (object)
- `requirements` (object)
- `workload` (object)

### `benchmark_results` (~79 tokens)

Get benchmark results

Get reviewed scores for an exact benchmark_id from benchmark_list. Join result.modelId to catalog_search model.id. Compare scores only within the same benchmark edition and configuration. Includes source provenance and reported coding-agent usage when published. Follow pagination.hasMore.

Input parameters:

- `benchmark_id` (string, required)
- `limit` (integer)
- `offset` (integer)

Output parameters:

- `data` (object)
- `meta` (object)
- `pagination` (object)

### `provider_list` (~48 tokens)

List inference providers

Discover accepted provider slugs, roles, and current comparable model/offer counts. Provider minimum input and output prices are independent minima and may belong to different models; use offer_compare for an actual quote.

Output parameters:

- `data` (object)
- `meta` (object)

### `benchmark_list` (~41 tokens)

Discover reviewed benchmarks

Discover exact benchmark IDs, editions, score units, configurations, provenance, and reviewed result counts before calling benchmark_results. Empty benchmarks are retained with resultCount 0.

Output parameters:

- `data` (object)
- `meta` (object)

### `coding_agent_list` (~73 tokens)

List coding agents

List coding-agent profiles, interfaces, model access, official sources, latest stable release, archive counts, freshness, coverage limits, and sourced model/provider compatibility, BYOK, billing and setup facts. Includes agents whose release archive is unavailable; inspect state. Use coding_agent_releases to page through source-linked changelogs.

Output parameters:

- `data` (object)
- `meta` (object)

### `coding_agent_detail` (~63 tokens)

Get a coding agent

Get a coding-agent profile by agent_slug from coding_agent_list, including official source, latest stable release, freshness, and history coverage. An unavailable archive is explicit in state. This does not assert product benchmark rankings or subscription prices.

Input parameters:

- `agent_slug` (string, required)

Output parameters:

- `data` (object)
- `meta` (object)

### `coding_agent_releases` (~148 tokens)

Search coding-agent changelogs

Search archived coding-agent releases by agent_slug, query (title, version, excerpt), topic, and channel. Stable only by default; channel all includes prereleases. Newest first; advance offset by limit while pagination.hasMore. Includes source URLs, abbreviated excerpts, and per-agent freshness/coverage. Topics are keyword mentions, not assessments. Partial coverage is explicit in meta.completeness; all unavailable returns an error. Archives reflect configured source history, not every product announcement.

Input parameters:

- `agent_slug` (string)
- `channel` (string)
- `limit` (integer)
- `offset` (integer)
- `query` (string)
- `topic` (string)

Output parameters:

- `data` (object)
- `meta` (object)
- `pagination` (object)

### `coding_agent_upgrade` (~156 tokens)

Changes since an installed agent version

Find archived changes published after an installed version or exact release ID. Get agent_slug and source_id from coding_agent_detail; default source_id is primary. Only the same publisher source and recognizable product stream are compared. Stable only by default; use channel all for prereleases. The ready response is publication order, not semantic-version precedence or an upgrade safety assessment; backports may appear. An unknown or ambiguous baseline is explicit in data.status, never treated as no changes. Follow data.pagination.hasMore with offset and limit.

Input parameters:

- `agent_slug` (string, required)
- `channel` (string)
- `installed` (string, required)
- `limit` (integer)
- `offset` (integer)
- `source_id` (string)

Output parameters:

- `data` (object)
- `meta` (object)

### `price_watch` (~363 tokens)

Check workload price savings

Read current offers meeting a monthly baseline_usd minus minimum_saving_usd. Uses the same workload, qualifications and evidence filters as offer_compare. Omit model_slugs to watch all qualifying models. Returns up to 50 cheapest matches; no account or delivery subscription is created. The same query is available as RSS at /api/v1/price-watch/feed.xml; your RSS reader handles polling and notifications. Inspect offer warnings before switching.

Input parameters:

- `average_input_tokens` (integer)
- `average_output_tokens` (integer)
- `baseline_usd` (number, required)
- `benchmark_id` (string)
- `cache_hit_percent` (number)
- `cache_write_percent` (number)
- `execution` (string): Batch supports Anthropic direct routes with a published 50% token discount; unsupported routes are excluded.
- `input_tokens` (integer)
- `limit` (integer)
- `minimum_context_tokens` (integer)
- `minimum_saving_usd` (number, required)
- `minimum_score` (number): Zero disables score qualification; a positive threshold excludes missing exact benchmark matches.
- `model_slugs` (array)
- `offset` (integer)
- `open_weights` (boolean)
- `output_tokens` (integer)
- `provider_slugs` (array)
- `require_known_host` (boolean): Exclude routes without a named underlying inference provider.
- `require_official_prices` (boolean): Require official paired input/output price verification. Cache rates may have different source provenance.
- `required_capabilities` (array)
- `retry_percent` (number)
- `route_type` (string)
- `task` (string): Coding requires the code capability; extraction requires structured output. Every offer must support chat.

Output parameters:

- `assumptions` (array)
- `data` (object)
- `meta` (object)
- `pagination` (object)
- `requirements` (object)
- `watch` (object)
- `workload` (object)

### `execute` (~241 tokens)

Run catalog code

Run a JavaScript async function in an isolated sandbox, composing catalog_search, model_detail, offer_compare, benchmark_results, provider_list, benchmark_list, coding_agent_list, coding_agent_detail, coding_agent_releases, coding_agent_upgrade, and price_watch as catalog.* methods. Return a small JSON value. Example: async () => { const page = await catalog.catalog_search({query: 'claude', page_size: 5}); return page.data.models.map(m => ({slug: m.slug, prices: m.bestOffer?.prices})); }. No network, secrets, or database binding is exposed. Shared worldwide execution budgets: 100 per UTC minute and 5000 per UTC day. Limits: 30 executions per client per minute (IPv6 /64), 20 catalog calls and read units (offer_compare and price_watch use 5), at most two concurrent calls, 5 seconds wall time, 50ms sandbox CPU, 32KiB code, 64KiB JSON output. JavaScript only; no imports or TypeScript syntax. Use /mcp?mode=code for only search + execute.

Input parameters:

- `code` (string, required)

Output parameters:

- `calls` (integer)
- `logs` (array)
- `result`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi#diagnostics

## Score history

- 2026-11-05: 24
- 2026-11-04: 24
- 2026-11-03: 24
- 2026-11-02: 24
- 2026-11-01: 24
- 2026-10-31: 24
- 2026-10-30: 24
- 2026-10-29: 24
- 2026-10-28: 24
- 2026-10-27: 24
- 2026-10-26: 24
- 2026-10-25: 24
- 2026-10-24: 24
- 2026-10-23: 24
- 2026-10-22: 75
- 2026-10-21: 74
- 2026-10-20: 34
- 2026-10-19: 24
- 2026-10-18: 73
- 2026-10-17: 72
- 2026-10-16: 72
- 2026-10-15: 72
- 2026-10-14: 71
- 2026-10-13: 73
- 2026-10-12: 73
- 2026-10-11: 72
- 2026-10-10: 72
- 2026-10-08: 71
- 2026-10-07: 70
- 2026-10-04: 66

## Common questions

### What is the Cheapest LLM API MCP server?

Cheapest LLM API is an MCP server listed in the public MCP registry as io.github.tehtelabs/cheapestllmapi. Compare LLM API prices, search models and providers, and access reviewed benchmark results. This page covers its hosted endpoint (https://cheapestllmapi.com/mcp).

### Is the Cheapest LLM API MCP server safe to use?

Cheapest LLM API scores 24 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 Cheapest LLM API MCP server expose?

Cheapest LLM API exposes 12 tools: catalog_search, model_detail, offer_compare, benchmark_results, provider_list, and 7 more. Their descriptions and schemas cost roughly 1,752 tokens of context every time the server is loaded.

### Does the Cheapest LLM API MCP server require authentication?

Its publisher declares no required credentials for Cheapest LLM API. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Cheapest LLM API MCP server still maintained?

Cheapest LLM API is still listed as active in the MCP registry. We last reached this channel on 5 November 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://cheapestllmapi.com/mcp
- Repository: https://github.com/tehtelabs/cheapestllmapi
- Website: https://cheapestllmapi.com/
- Changelog RSS feed: https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi.xml
- Changelog JSON feed: https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi.json
- HTML version of this page: https://verifymcp.io/servers/tehtelabs-cheapestllmapi/cheapestllmapi