InferIndex

Cheapest offers for a model

cheapest

Read-onlyIdempotent

Cheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1). Stale prices, and flex/batch tiers, are excluded by default. Optional filters (context, tools, JSON, vision, region, no training on prompts, open sign-up) and usage (tokens per request, requests per day) to get an estimated cost per request and per month. Returns the winner in detail and one short line per following offer. A condition that is absent was not published by the provider, it never means "no"; a flag not listed in signals is false.

Input Schema

TableJSON Schema

Name	Required	Description
`json`	No	Only offers that support JSON output
`limit`	No	Number of offers to return, winner included (default 5, max 25)
`model`	Yes	Model id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
`tools`	No	Only offers that support tool calling
`detail`	No	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
`region`	No	Only providers that process data in this region: eu, us, …
`strict`	No	Exclude offers whose provider does not publish the filtered information (by default they are kept and flagged)
`vision`	No	Only offers that accept image input
`min_context`	No	Minimum context window in tokens
`no_training`	No	Only providers whose published terms say they do not train on your prompts
`no_waitlist`	No	Only providers with open sign-up (no waitlist, invitation or country restriction)
`cached_ratio`	No	Share of input tokens served from the provider's prompt cache (0 to 1)
`include_tiers`	No	Also include lower-priority service tiers, comma-separated: flex, batch (hidden by default)
`output_tokens`	No	Output tokens per request, for the estimated cost
`prompt_tokens`	No	Input tokens per request, for the estimated cost
`requests_per_day`	No	Requests per day, to also get an estimated monthly cost

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 5, 2026

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 5, max 25)"New value: +"Number of offers to return, winner included (default 5, max 25)"

Changed1 schema field changedOct 5, 2026

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)"

First observedSep 18, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With annotations already declaring readOnly/idempotent/non-destructive, the description adds real semantic context: default exclusion of stale prices and flex/batch tiers, and the important interpretation rule that an absent condition means 'not published', never 'no', and that unlisted flags are false. It does not discuss rate limits or fresh-vs-cached data timeliness.

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?

Front-loaded with the core purpose and price unit, then filters, then return shape. Sentences are dense but every clause carries information; the interpretation rule about absent conditions is worth its length.

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 16-parameter tool with no output schema and no destructive semantics, the description covers purpose, default behavior, filters, return shape, and interpretation of missing data. A brief pointer to which sibling to use when would make it fully complete.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description adds meaning beyond the schema by explaining the default behavior of detail (compact winner+short lines), default limit (5), and the strict/absent-condition interaction. This helps the agent interpret filters correctly rather than just pass them.

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

Purpose5/5

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

States a specific verb+resource+scope: current cheapest API offers for one model across direct providers and aggregators, with the price unit (USD per 1M tokens, input/output/blended 3:1). This clearly separates it from siblings like compare_providers and price_history.

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?

Usage is implied rather than stated: it explains default exclusions (stale prices, flex/batch tiers) and that optional filters can narrow results, but never says when to prefer this over compare_providers or estimate_cost. The one routing hint (use search_models when unsure) lives in the schema, not the description.

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

All InferIndex tools Inspect

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.

Cheapest offers for a model

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources