api14
Get API key

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.

Elorian: Glimpse vs Inception: Mercury 3

A side-by-side comparison of Elorian: Glimpse ($2.10 / 1M tokens) and Inception: Mercury 3 ($0.35 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

Elorian: GlimpseInception: Mercury 3
ProviderElorianInception
Input$2.10 / 1M tokens$0.35 / 1M tokens
Output$10.50 / 1M tokens$1.22 / 1M tokens
Cache read$0.21 / 1M tokens$0.04 / 1M tokens
Context window262,1441,000,000
Max output256,000131,072
Inputtext, image, videotext
Outputtexttext
Tool calling
Structured output
Reasoning control
AddedOct 17, 2026Oct 16, 2026

Key differences

  • Inception: Mercury 3 is 83% cheaper on input tokens.
  • Inception: Mercury 3 is 88% cheaper on output tokens.
  • Inception: Mercury 3 reads 3.8× more context (1,000,000 tokens).
  • A request with 1,000 input and 500 output tokens costs $0.00735 with Elorian: Glimpse and $0.000963 with Inception: Mercury 3.

Switch with one string

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

Elorian: Glimpse details & playground →Inception: Mercury 3 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": "inception/mercury-3",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

More comparisons