How much does Mercury 3 cost on Zeplik?

Input tokens cost 1.2 credits per million and output tokens 4.2 credits per million (1 credit = $0.10; the raw provider rates are $0.10 and $0.35 per million). New accounts start with free credits.

How long can a conversation with Mercury 3 be?

Mercury 3 has a 1M-token context window (1,000,000 tokens), which covers the conversation plus any documents you attach.

Does Mercury 3 support images and tools?

Mercury 3 is text-only and supports tool calling.

Mercury 3

General purposeTools

Inception · Released October 2026

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date.

It is part of Inception's Mercury line of diffusion language models, which generate tokens in parallel rather than sequentially and are built for speed.

Facts and pricing

Provider: Inception
Context window: 1M tokens
Input price: 1.2 credits / 1M tokens ($0.10 raw)
Output price: 4.2 credits / 1M tokens ($0.35 raw)
Vision (image input): No
Tool calling: Yes
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Try Mercury 3 now

Or open Zeplik with Mercury 3 already selected

What Mercury 3 is best for

Balanced everyday work: writing, questions, brainstorming and summarization
Very long documents and codebases: a 1M-token window fits entire books or repositories in one conversation
Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Example prompts

Prompts that suit a general purpose model like Mercury 3:

Help me outline a talk about what I learned this year
Compare these two paragraphs and tell me which is clearer and why
Draft a polite reply declining this invitation
Explain this concept with a concrete everyday analogy

Inception family

Model	Context	Input cr/M	Output cr/M	Released
Mercury 3	1M	1.2	4.2	October 2026
Mercury 2.5	260K	0.48	1.8	September 2026
Mercury 2	128K	3.0	9.0	March 2026

Model comparisons

Frequently asked questions

What is Mercury 3?: Mercury 3 is an AI model by Inception. Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date.
How much does Mercury 3 cost on Zeplik?: Input tokens cost 1.2 credits per million and output tokens 4.2 credits per million (1 credit = $0.10; the raw provider rates are $0.10 and $0.35 per million). New accounts start with free credits.
How long can a conversation with Mercury 3 be?: Mercury 3 has a 1M-token context window (1,000,000 tokens), which covers the conversation plus any documents you attach.
Does Mercury 3 support images and tools?: Mercury 3 is text-only and supports tool calling.

Related models

Mercury 2.5General purpose

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.

260K ctx1.8 cr/M outSeptember 2026

Mercury 2General purpose

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).

128K ctx9.0 cr/M outMarch 2026

ricursiveAI/Ripple-65B-PreviewGeneral purpose

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

16K ctx7.2 cr/M outNovember 2026

Hy4General purpose

1.0M ctx15.0 cr/M outNovember 2026

Crouton AlphaGeneral purpose

Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work.

1.0M ctx0 cr/M outNovember 2026

GLM 5.3 FlashX LegalFast and light

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text.