Skip to main content
Glama

InferIndex

by io.github.InferIndex
OverviewDiscussionsAdmin

Compare providers for a model

compare_providers
Read-onlyIdempotent

Current offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, quantization, signals and training on prompts when published; the cheapest offer comes in detail. Pass detail: "full" for context, every published condition (data regions, sign-up) and reliability from official status pages on each offer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort order (default blended); estimated_cost needs prompt_tokens or output_tokens
limitNoNumber of offers to return, cheapest included (default 10, max 50)
modelYesModel id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
detailNocompact (default): the winner in detail and one short line per other offer (provider, prices, signals, training on prompts when published). full: every field of every offer (all published conditions, reliability), much longer
regionNoOnly providers that process data in this region: eu, us, …
strictNoExclude offers whose provider does not publish the filtered information (by default they are kept and flagged)
no_trainingNoOnly providers whose published terms say they do not train on your prompts
no_waitlistNoOnly providers with open sign-up (no waitlist, invitation or country restriction)
cached_ratioNoShare of input tokens served from the provider's prompt cache (0 to 1)
include_tiersNoAlso include lower-priority service tiers, comma-separated: flex, batch (hidden by default)
output_tokensNoOutput tokens per request, for the estimated cost
prompt_tokensNoInput tokens per request, for the estimated cost
requests_per_dayNoRequests per day, to also get an estimated monthly cost

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / detail
      Added value: +{
+  "description": "compact (default): the winner in detail and one short line per other offer (provider, prices, signals, training on prompts when published). full: every field of every offer (all published conditions, reliability), much longer",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / limit / description
      Previous value: -"Number of offers to return (default 10, max 50)"New value: +"Number of offers to return, cheapest included (default 10, max 50)"
  2. Changed1 schema field changed
    • changedInput schema / properties / no_waitlist / description
      Previous value: -"Only providers with open sign-up (no waitlist or invitation)"New value: +"Only providers with open sign-up (no waitlist, invitation or country restriction)"
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds real behavioral value on top: default result count, cheapest-first ordering, the default-vs-full verbosity tradeoff, and that providers lacking published info are kept and flagged unless `strict` is set. It does not describe pagination or how missing data appears in output, but the annotation bar is met.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core behavior (what a row is, ordering, default size, winner-in-detail). Both sentences carry information, though the second is long and slightly run-on with its list of caveats.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter comparison tool with no output schema, the description covers the result shape and the compact/full distinction well enough to call it correctly. Remaining gaps (pagination, precise flagging format) are minor given the annotations and high schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 13 parameters, including the two enums. The description restates the `detail` semantics (context, published conditions, status-page reliability) but adds little that the schema does not already carry, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource precisely (current offers for one model, one line per provider and source) and the ordering (cheapest first, 10 by default), which lets an agent distinguish it from `cheapest` and `estimate_cost`. It stops short of explicitly contrasting itself with those siblings, so a 4 rather than a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear when-to-use for the `detail: "full"` option, but never says when to reach for this tool over `cheapest`, `estimate_cost` or `price_history`, nor does it state prerequisites for the comparison. Usage is implied rather than routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All InferIndex toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources