- - 🆕 Diffusion-based reasoning LLM from Inception Labs.
- - ⚡ Provider describes throughput exceeding 1,000 tokens per second.
- - 🧠 Built for reasoning, not just fast generation.
- - 📏 128K-token context window.
- - 🔧 Native function calling and structured output support.
- - 🌐 Adds integrated web search to its capability set.
- - 🎯 Generates and refines tokens in parallel rather than one at a time.
- - 🏢 Aimed at latency-sensitive agent and pipeline workloads.
Inception Labs builds large language models powered by diffusion rather than the autoregressive generation most LLMs rely on. Instead of producing text one token at a time, its diffusion LLMs (dLLMs) generate many tokens in parallel, which makes them several times faster and…
Explore 2 more models by Inception Labs →Mercury 2 is a diffusion-based large language model released in 2026 by Inception Labs, an AI startup focused on bringing the diffusion paradigm to language modeling. Unlike conventional autoregressive transformers that generate text strictly one token at a time, diffusion language models produce and iteratively refine spans of output in parallel — a coarse-to-fine approach adapted from the denoising process used in image generation.
According to its catalog description, Mercury 2 is positioned as a reasoning-capable model rather than a purely speed-optimized one, combining parallel diffusion decoding with reasoning, tool use, and structured output. Inception describes throughput exceeding 1,000 tokens per second, which the company frames as the model's headline advantage for workloads where generation latency matters.
The model ships with a 128,000-token context window and supports function calling and integrated web search, making it suited to agentic loops, retrieval pipelines, and extraction tasks where many sequential model calls compound latency.
Within Inception's own lineage, Mercury 2 extends the company's earlier diffusion language-model efforts, which began with code-generation systems, into a more general reasoning model with agentic tooling. Independent, third-party benchmark replication was not available among the sources reviewed here, so specific quality figures are omitted; the description above reflects the model's documented architecture and capabilities rather than performance rankings.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Mercury 2 · Organic sellers
Top sellers · Mercury 2 · Organic
- Venice.ai Proxy96.7%
- ▲ Apex Ant3.3%
- Fire Ant 🔥🐜0.0%
- Super Seeder0.0%
- Sapiens0.0%
| Seller | Rep↓ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save |
|---|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 81.71 | $0.05 | 245.85k | #1 | $0.31 | $0.31 | $0.94 | −1% |
| surplus-hive 0x6145…5c58 | 0.00 | — | — | gated | $0.7595 | $0.7595 | $2.2786 | — |
| antseed-neon-puma-944e 0x6650…944e | 0.00 | — | — | gated | $0.1066 | $0.0313 | $0.3197 | −66% |
| Apex TEE Test 0xe672…7955 | 0.00 | — | — | gated | $0.0844 | $0.0844 | $0.2531 | −73% |
| Meridian AI 0x8c8c…06f5 | 0.00 | — | — | gated | $0.0672 | $0.0672not advertised | $0.2015 | −79% |
| Leftermute 0x388b…5389 | 0.00 | — | — | gated | $0.0631 | $0.0631not advertised | $0.1894 | −80% |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.