Aayat AI

Chat fast ($0.003)

chat-fast

Read-only

Pay-per-call LLM chat (Llama 3.2 3B): Fast, cheap model for classification, extraction, short answers and routing. No API key or account. POST JSON {"prompt": "..."} or OpenAI-style {"messages": [{"role": "user", "content": "..."}]}, optional "system", "max_tokens" (up to 1024), "temperature", "json": true. Up to about 15,000 characters of English in. Failed calls are not charged. Price: $0.003 in USDC per call (x402 or prepaid credits). In the free trial.

Input Schema

TableJSON Schema

Name	Required	Description
`json`	No	Ask for JSON-only output.
`prompt`	No	A single user message (use this or messages).
`system`	No	System instructions.
`messages`	No	Conversation so far, OpenAI style: [{role, content}].
`max_tokens`	No	Most tokens to generate (default 512).
`temperature`	No	Randomness, 0-2.

Output Schema

TableJSON Schema

Name	Required	Description
`text`	Yes	The model's reply.
`model`	Yes	The model that answered.
`usage`	Yes
`fallbackFrom`	No	Only when the tier's own model was unavailable: the model you asked for (a stand-in answered).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 28, 2026

addedOutput schema / properties / fallbackFrom

Added value: +{
+  "description": "Only when the tier's own model was unavailable: the model you asked for (a stand-in answered).",
+  "type": "string"
+}

addedOutput schema / properties / model / description
```
Added value: +"The model that answered."
```

First observedSep 28, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: no API key or account needed, ~15,000 character input ceiling, failed calls are not charged, $0.003 USDC per call via x402 or prepaid credits, and current free-trial status. This pricing/billing/auth disclosure is exactly the kind of behavior annotations cannot convey.

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 model and its purpose, then price and payload formats; every clause carries information. It is dense and slightly run-on with several embedded facts, but nothing is wasted.

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

Completeness5/5

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

An output schema exists so return values need no explanation; the description covers pricing, auth, input limits, failure billing, and accepted request shapes. Nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so the baseline is 3. The description echoes the schema's own guidance (prompt vs OpenAI-style messages, optional system/max_tokens/temperature/json) and adds only the note that max_tokens tops out at 1024, which the schema already encodes as a maximum.

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 (pay-per-call LLM chat), names the exact model (Llama 3.2 3B), and characterizes its niche (fast, cheap, for classification/extraction/short answers/routing) so it is distinguishable from the sibling chat and chat-premium tools at a glance.

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

Usage Guidelines4/5

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

Gives clear positive context — use this for cheap, fast tasks like classification, extraction, short answers and routing — which implicitly separates it from the premium sibling. It never states when NOT to use it or names chat-premium as the alternative for harder tasks, so the routing condition is left to inference.

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

All Aayat AI 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.

Resources

Need Help?