Inception Labs launched Mercury 3, a diffusion language model that generates 1,068 tokens per second - 4-8x faster than GPT-6 Luna - while matching its quality. It has a 1M token context window, costs $0.10/M input tokens, and ships with specialized voice and structured-decision models. This is the first proof that diffusion LLMs scale to compete with autoregressive models on both speed and quality.
# Why Diffusion Changes Everything
Every LLM you use today is autoregressive. GPT-6, Claude, Gemini, Llama - they all generate tokens one at a time, left to right. Each token waits for the previous one. That sequential bottleneck is why inference is slow and expensive, no matter how much hardware you throw at it.
Mercury 3 is a diffusion language model. Instead of predicting one token at a time, it starts with noise across the entire output and iteratively refines all tokens in parallel. Think of it like a sculptor revealing a statue from a block of marble rather than building it brick by brick. The result: massive parallelism that scales with GPU cores rather than sequence length.
One token at a time, sequential. Speed limited by depth, not width.
All tokens refined in parallel. Speed scales with GPU width.
Mercury 3 is 40x larger than Mercury 1 (their first diffusion model) yet achieves comparable speed. That scaling trajectory is the real story. If diffusion models maintain speed as they grow, the autoregressive bottleneck becomes a competitive disadvantage.
# How It Stacks Up
Inception claims quality on par with GPT-6 Luna and Claude Haiku 5.5. Here is what the numbers look like side by side.
| Metric | GPT-6 Luna | Claude Haiku 5.5 | Mercury 3 |
|---|---|---|---|
| Speed (tok/s) | ~150-250 | ~180-280 | 1,068 |
| Context window | 256K | 200K | 1M |
| Input price (per 1M) | $1.25 | $0.80 | $0.10 |
| Output price (per 1M) | $5.00 | $4.00 | $0.35 |
| Generation approach | Autoregressive | Autoregressive | Diffusion |
The context window jumped from 260K (Mercury 2.5) to 1M tokens. The pricing includes a launch 50% discount, but even at full price ($0.20 input / $0.70 output) it undercuts every comparable model by 4-10x. These are the numbers that make platform teams rewrite their cost projections.
# Beyond the Base Model
Inception did not just ship a faster model. They shipped a product suite targeting the two use cases where speed matters most: voice and structured decisions. CEO Stefano Ermon (Stanford professor, diffusion model pioneer) is betting that speed-sensitive applications are where diffusion wins first.
Purpose-built for real-time voice agents. Time-to-first-token under 170ms - fast enough that voice conversations feel natural with no perceptible delay. At 1,068 tok/s, the model finishes generating before the TTS engine needs the next chunk.
A structured decision model that outputs calibrated probabilities instead of free-form text. Feed it a decision with options, get back ranked choices with confidence scores. Designed for routing, classification, and agentic tool selection where you need reliable structured output at extreme speed.
OpenAI API compatible. Drop-in replacement - swap the base URL and API key, keep your existing code. No SDK changes, no prompt rewrites.
# Before (OpenAI) client = OpenAI( api_key="sk-...", # base_url defaults to api.openai.com ) # After (Mercury 3) - change two lines client = OpenAI( api_key="mercury-...", base_url="https://api.inceptionlabs.ai/v1", ) # Everything else stays the same response = client.chat.completions.create( model="mercury-3", messages=[{"role": "user", "content": "..."}], )
# Why This Matters Right Now
Mercury 3 is not just a faster model. It is the first credible proof that the autoregressive paradigm has a real competitor. Here is what engineers should pay attention to.
At 1,068 tok/s, you can run inference in real-time loops: voice agents, live coding assistants, game NPCs, and interactive tutors that respond faster than human perception. These applications were cost-prohibitive with autoregressive models.
At $0.10/M input and $0.35/M output, you can process 10x more tokens for the same budget. Batch jobs that cost $500/day on GPT-6 Luna could drop to $40. That is the difference between "prototype only" and "ship to production."
Mercury 3 is 40x larger than Mercury 1 with comparable speed. Autoregressive models get slower as they scale. Diffusion models get smarter at the same speed. If this trajectory holds, the next generation could match GPT-6 Pro quality at Mercury 3 prices.
OpenAI API compatibility means you can test Mercury 3 in your existing stack without changing a single line of application code. Swap the base URL, run your eval suite, and compare. The switching cost is effectively zero.
Mercury 3 is the moment diffusion LLMs stopped being a research curiosity. 1,068 tokens per second, 1M context, GPT-6 Luna quality, and pricing that makes autoregressive models look like luxury goods. Inception Labs, led by Stanford's Stefano Ermon, just gave every team building speed-sensitive AI applications a reason to run benchmarks this week. The question is no longer "will diffusion LLMs work?" - it is "how fast will they improve?"
Enjoyed this?
New episodes Mon, Wed, Sat.