We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.

New here? See how it works A 1-minute tour of the playground, models and your API key.

Clef vs Mercury Decide: API price, context & features · api14

Cloudflare: Clef vs Inception: Mercury Decide

A side-by-side comparison of Cloudflare: Clef ($0.67 / 1M tokens) and Inception: Mercury Decide ($0.07 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Cloudflare: Clef	Inception: Mercury Decide
Provider	Cloudflare	Inception
Input	$0.67 / 1M tokens	$0.07 / 1M tokens
Context window	65,537	65,536
Max output	58,983	58,982
Input	text, image	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 2026	Sep 30, 2026

Key differences

Inception: Mercury Decide is 90% cheaper on input tokens.
A request with 1,000 input and 500 output tokens costs $0.000672 with Cloudflare: Clef and $0.000070 with Inception: Mercury Decide.

In depth

Cloudflare: Clef is a decision model from Cloudflare, and Inception: Mercury Decide is a decision model from Inception. Both are listed under the decisions category, and both were released within a day of each other in late 2026, Mercury Decide on September 30 and Clef on October 1. They are close siblings in purpose: you call one when you want a model to return a decision rather than free-form prose.

Their capability profiles are nearly identical on paper. Both accept text and image input, both emit decisions as their only output modality, and both expose no tunable parameters, so there is nothing to configure beyond the prompt and the model id. The context windows are effectively the same size, 65537 tokens for Clef and 65536 for Mercury Decide, a one-token difference that will not change any real workload. Neither model is flagged as the only one supporting tools, structured output or reasoning, so on those axes there is no meaningful separation. The one qualitative difference given is price: Mercury Decide is the cheaper of the two on input tokens. Output pricing is listed as about the same, so the cost gap, whatever it is, comes from the input side.

For most tasks the choice comes down to that input cost. If your workload is input-heavy, meaning long documents, large image sets, big retrieved contexts or repeated calls over the same bulky prompt, Mercury Decide is the cheaper option and the natural default. If your workload is output-heavy or roughly balanced, the two are close enough that either will do, and you can pick on other grounds such as which provider you already trust or which one your evaluation happens to favour. Since both take images, both are viable for tasks that mix screenshots, scans or diagrams with text. Because neither model supports tunable parameters, there is no sampling or temperature tuning to weigh in the decision, which removes one common reason to prefer one over the other.

Calling either model through api14 is the same operation. The API is OpenAI-compatible, so you point your existing client at the api14 base URL, send your request in the usual chat completions shape, and set the model field to either "cloudflare/clef" or "inception/mercury-decide". Nothing else in the request body needs to change: same messages array, same image content parts, same authentication header. Switching between the two is a one-string edit, which makes it cheap to route a given request to whichever model you prefer and to A/B the two on your own traffic.

There is one case where Clef is still the better pick despite Mercury Decide being cheaper on input. If your evaluation shows Clef producing the decisions you want more reliably, or if you have already built around Cloudflare and want to stay within that provider, the small input price difference is unlikely to outweigh a quality or operational preference. The facts here do not establish that either model is more accurate, so treat the price difference as the only hard tiebreaker and let your own testing settle the rest.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "cloudflare/clef" to "inception/mercury-decide" and prompts, streaming and tools keep working.

Cloudflare: Clef details & playground →Inception: Mercury Decide details & playground →

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.post("/decisions", { body: {
  "model": "inception/mercury-decide",
  "state": "Customer: I was charged twice for my order and want my money back.",
  "questions": {
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this message?",
      "criteria": {
        "billing": "Payments, refunds, invoices",
        "support": "Product questions and bugs",
        "sales": "Pricing and new purchases"
      }
    },
    "urgent": {
      "type": "noul",
      "instructions": "Does this need a reply today?",
      "criteria": {
        "true": "Money, outage or legal risk",
        "false": "Can wait"
      }
    }
  }
} });
console.log(result.answers);

Cloudflare: Clef vs Inception: Mercury Decide

Specifications

Key differences

In depth

Switch with one string

More comparisons