Inception

Inception Mercury 3

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

Try in consoleGet an API key
Context window
1Mtokens
Max output
131Ktokens
Input
$0.10/ 1M
Output
$0.35/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

completion = client.chat.completions.create(
    model="inception/mercury-3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Cost

Example requestTokensCost
Short prompt1K in$0.0001
Typical chat turn1K in · 500 out$0.000275
Document analysis10K in · 2K out$0.0017
Long context100K in · 10K out$0.0135
Estimated cost per request$0.000275

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is Inception Mercury 3?

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

How much does Inception Mercury 3 cost?

Inception Mercury 3 is priced at $0.1 per 1 million input tokens and $0.35 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does Inception Mercury 3 support streaming?

Yes, Inception Mercury 3 supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of Inception Mercury 3?

Inception Mercury 3 has a context window of 1.0M tokens (~750K words). Maximum output is 131K tokens.

Does Inception Mercury 3 support function calling (tools)?

Yes, Inception Mercury 3 supports function calling / tool use via NeuronGate's standard API.

How do I use Inception Mercury 3 with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id inception/mercury-3 in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.