Inception: Mercury 3 vs MiniMax: MiniMax M3.1 Flash

A side-by-side comparison of Inception: Mercury 3 ($0.35 / 1M tokens) and MiniMax: MiniMax M3.1 Flash ($0.52 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Inception: Mercury 3	MiniMax: MiniMax M3.1 Flash
Provider	Inception	MiniMax
Input	$0.35 / 1M tokens	$0.52 / 1M tokens
Output	$1.22 / 1M tokens	$2.10 / 1M tokens
Cache read	$0.04 / 1M tokens	$0.05 / 1M tokens
Context window	1,000,000	1,000,000
Max output	131,072	524,288
Input	text	text, image, video
Output	text	text
Tool calling
Structured output
Reasoning control
Added	Oct 16, 2026	Oct 19, 2026

Key differences

Inception: Mercury 3 is 33% cheaper on input tokens.
Inception: Mercury 3 is 42% cheaper on output tokens.
Only Inception: Mercury 3 supports structured JSON output.
A request with 1,000 input and 500 output tokens costs $0.000963 with Inception: Mercury 3 and $0.00158 with MiniMax: MiniMax M3.1 Flash.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "inception/mercury-3" to "minimax/minimax-m3.1-flash" and prompts, streaming and tools keep working.

Inception: Mercury 3 details & playground →MiniMax: MiniMax M3.1 Flash 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.chat.completions.create({
  "model": "minimax/minimax-m3.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

Inception: Mercury 3 vs MiniMax: MiniMax M3.1 Flash

Specifications

Key differences

Switch with one string

More comparisons