InceptionText Generation/v1/ai/chat

Mercury 3 API

Access Mercury 3 through one API key. Inception Diffusion LLM for Low Latency.

Mercury 3 is a diffusion-based language model from Inception, the lab's most capable model to date. It is built for agentic workflows and real-time applications where latency compounds, such as voice agents, autocomplete and many-step tool loops.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

Mercury 3 API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.

Token type	Price
Input	$0.15 / 1M tokens
Output	$0.52 / 1M tokens
Context window	1M tokens

What it costs	Per job	Per 1,000
Chat reply1K input + 500 output tokens	$0.0004	$0.41
RAG answer8K input + 800 output tokens	$0.0016	$1.62
Agent step with tools30K input + 2K output tokens	$0.0055	$5.54
Long document summary100K input + 2K output tokens	$0.016	$16.04

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Mercury 3 respond in real time.

POST/v1/ai/chatinception/mercury-3

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

Mercury 3 specs

Provider	Inception
Model ID	inception/mercury-3
Endpoint	/v1/ai/chat
Type	Text Generation
Context window	1M tokens
Max output	131K tokens
Reasoning	No
OpenAI-compatible	Yes — /v1/ai/chat/completions

How to get a Mercury 3 API key

1
Create a free account
Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.
2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
3
Call Mercury 3
Send a request to /v1/ai/chat with the x-api-key header and model "inception/mercury-3".
4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓

Diffusion architecture

Generates text in parallel rather than token by token, for very fast responses.

✓

Low latency agents

Suited to loops with many sequential calls, where per-call latency adds up.

✓

1M token context

Up to 1,000,000 input tokens and 131,072 output tokens per call.

✓

Low cost

$0.15 per 1M input and $0.52 per 1M output tokens.

Quick start

Copy this snippet and start making calls with Mercury 3.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "inception/mercury-3",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Mercury 3 vs similar models

Every model below runs on the same API key — switch by changing the model ID.

Model	Provider	Price	Context
Mercury 3	Inception	$0.15 in / $0.52 out per 1M	1M
Nemotron 3 Super	NVIDIA	$0 in / $0 out per 1M	262K
Qwen3.7 Flash	Qwen	$0.04 in / $0.19 out per 1M	1M
Solar Mini 4	Upstage	$0.07 in / $0.30 out per 1M	524K
Nemotron 3.5 Lightning	NVIDIA	$0.10 in / $0.30 out per 1M	262K
DeepSeek V4 Flash	DeepSeek	$0.13 in / $0.27 out per 1M	1.0M
Qwen 3.5 Flash	Qwen	$0.10 in / $0.38 out per 1M	1M
Seed 1.6 Flash	ByteDance	$0.11 in / $0.44 out per 1M	262K

Why use Mercury 3 through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

Mercury 3 API — pricing, context window & access

Mercury 3 is a diffusion-based language model from Inception, the lab's most capable model to date. It pairs a 1,000,000-token context window with up to 131,072 output tokens per response, at $0.15 per 1M input and $0.52 per 1M output tokens through YepAPI.

Through YepAPI you call Mercury 3 on an OpenAI-compatible endpoint with a single key — the same key that reaches GPT-6, Claude, Gemini, Grok and the SEO, SERP and scraping APIs. Input: text.

What is Mercury 3?

Mercury 3 is a diffusion-based language model from Inception, the lab's most capable model to date. Instead of writing one token at a time, a diffusion model refines a whole response in parallel, which makes generation very fast. It accepts text as input, handles up to 1,000,000 tokens of context and returns up to 131,072 output tokens per call.

Build with Mercury 3 via YepAPI

YepAPI serves Mercury 3 on the OpenAI-compatible /v1/ai/chat endpoint. Point your base URL at YepAPI, add your key, and set the model string to mercury-3 (or the full inception/mercury-3). Function calling, structured outputs and reasoning settings pass straight through, and switching to any other model on the platform is a one-string change per request.

Mercury 3 API pricing — $0.15 / 1M input, $0.52 / 1M output

Mercury 3 costs $0.15 per 1M input tokens and $0.52 per 1M output tokens through YepAPI, pay per token with no minimums. Failed calls are never charged, and every request is itemised in your dashboard API Logs.

Mercury 3 use cases

It is built for agentic workflows and real-time applications where latency compounds, such as voice agents, autocomplete and many-step tool loops.

Try Mercury 3 free

Every new YepAPI account includes $5 in free credit with no card required — enough to test Mercury 3 on your own prompts before committing to paid usage. Create an account, copy your key, and call mercury-3 right away.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
Marcus T.
SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
Priya S.
Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Jake R.
Indie Hacker

Frequently asked questions

Mercury 3 costs $0.15 per 1M input tokens and $0.52 per 1M output tokens through YepAPI, billed per request with no monthly fee. For example, a chat reply (1K input + 500 output tokens) costs about $0.0004.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Mercury 3 and every other model — no separate Inception account or waitlist.

New YepAPI accounts in most countries get free signup credit, enough to test Mercury 3 without a card. After that you pay per request at the rates above — there is no subscription.

Use "inception/mercury-3" as the model on /v1/ai/chat. The short alias "mercury-3" also works.

Yes. Point the OpenAI SDK at https://api.yepapi.com/v1/ai with your YepAPI key and set model to "inception/mercury-3". Streaming works the same way, so existing OpenAI code only needs the base URL and key changed.

Mercury 3 supports a 1M token context window with up to 131K output tokens per request.