# Inception Mercury 3: 1,068 Tokens/s, Price, Benchmarks

> Inception's Mercury 3 diffusion LLM runs 1,068 tokens/s at $0.10/$0.35 launch pricing. Its benchmarks vs GPT-6 Luna and Claude Haiku 5.5, row by row.

- Author: Nitish Garg, Founder & CEO, CellCog
- Published: 2026-10-19
- Canonical (HTML): https://cellcog.ai/blog/inception-mercury-3/
- Section: Guides / Choosing a platform
- Publisher: CellCog (https://cellcog.ai), the AI employee platform. Blog index for agents: https://cellcog.ai/blog/llms.txt

## Key points

- Inception released Mercury 3 on October 19, 2026, a diffusion LLM that refines a whole answer in parallel instead of writing it one token at a time. Inception says it is more than 40x larger than Mercury 1.
- Inception measures it at 1,068 tokens per second on NVIDIA GPUs, against about 240 for Claude Haiku 5.5 and about 130 for GPT-6 Luna in its own table.
- Launch price is $0.10 input and $0.35 output per million tokens, 50% off. The list price is $0.20 and $0.70, which puts output above both rivals' $0.50.
- On Inception's 12 capability rows, Mercury 3 leads 8. GPT-6 Luna leads AA-Omniscience and AA-LCR; Claude Haiku 5.5 leads MRCR v2 and DeepSWE.
- Every benchmark number is Inception's own run, in medium settings for all three models. It is available on Inception's API, OpenRouter, Baseten and Vercel, with a 1M-token context.

## At a glance

- **What is Mercury 3?** Inception's third-generation diffusion language model, released October 19, 2026, aimed at latency-sensitive work such as voice support, tutoring, search and browser agents.
- **How fast is it?** 1,068 tokens per second on NVIDIA GPUs by Inception's measure, about 4x Claude Haiku 5.5 and 8x GPT-6 Luna in the same table.
- **What does it cost?** $0.10 input and $0.35 output per million tokens at launch, 50% off the $0.20 and $0.70 list price. Cached input is 90% off.

**Inception released Mercury 3 on October 19, 2026, and its pitch is one number: 1,068 tokens per second.** Mercury 3 is a diffusion language model. Instead of writing an answer one token after another, it refines the whole answer in parallel over a few passes, which is why Inception can put it at 4 to 8 times the speed of GPT-6 Luna and Claude Haiku 5.5 in its own benchmark table.

The bigger claim is about scale. "Mercury 3 demonstrates that text diffusion scales." Inception says the model is more than 40x larger than Mercury 1 and that "The scaling laws that drove progress in autoregressive models hold for diffusion too." It ships with a 1M-token context and a 50% launch discount, on the [Inception API](https://www.inceptionlabs.ai/blog/introducing-mercury-3), [OpenRouter](https://openrouter.ai/inception/mercury-3), Baseten and Vercel.

## Speed and price against its class

![Animation: two lanes write the same six-word sentence; the top fills one word per step, the bottom starts as grey noise and sharpens all six words in three passes, finishing first](https://cellcog.ai/blog/media/inception-mercury-3/mercury-diffusion.svg)
*A normal model fills one word at a time; a diffusion model sharpens the whole answer*

*Table: Mercury 3 vs GPT-6 Luna vs Claude Haiku 5.5: speed and price (Inception table; vendor price pages)*

| | Mercury 3 | GPT-6 Luna | Claude Haiku 5.5 |
|---|---|---|---|
| Output speed (tokens/s, Inception's measure) | 1,068 | ~130 | ~240 |
| Input, $ per 1M tokens | $0.10 launch ($0.20 list) | $0.10 | $0.10 |
| Output, $ per 1M tokens | $0.35 launch ($0.70 list) | $0.50 | $0.50 |
| Context | 1M | not in Inception's table | 1M |

The price comparison depends on the date. At the launch discount, Mercury 3 matches both rivals on input and undercuts them on output. Inception lists the full price as $0.20 input and $0.70 output, and at that price output costs more than [Claude Haiku 5.5](https://platform.claude.com/docs/en/about-claude/pricing) and [GPT-6 Luna](https://developers.openai.com/api/docs/pricing), both $0.50 per million output tokens on their own pricing pages. Inception does not say when the discount ends. One more wrinkle on long inputs: Anthropic charges $0.50 input and $2.50 output for Haiku 5.5 prompts over 100,000 tokens.

## The benchmark table, row by row

*Table: Mercury 3 benchmarks vs GPT-6 Luna and Claude Haiku 5.5, all medium settings (Inception, October 19, 2026)*

| Benchmark | Mercury 3 | GPT-6 Luna | Claude Haiku 5.5 | Leader |
|---|---|---|---|---|
| GDPval (Elo) | 1,237.2 | 1,204.0 | 1,225.0 | Mercury 3 |
| t3-bench Banking | 30.24 | 23.00 | 13.06 | Mercury 3 |
| MultiChallenge | 60.35 | 51.49 | 52.48 | Mercury 3 |
| AA-Omniscience-Public (accuracy) | 46.44 | 46.94 | 37.22 | GPT-6 Luna |
| IFBench | 76.84 | 61.82 | 54.65 | Mercury 3 |
| GPQA Diamond | 89.23 | 86.36 | 84.51 | Mercury 3 |
| AA-LCR v1.1 | 77.67 | 78.30 | 74.70 | GPT-6 Luna |
| MRCR v2 | 75.50 | 62.72 | 78.40 | Claude Haiku 5.5 |
| SWE-Bench Atlas | 51.08 | 33.33 | 32.26 | Mercury 3 |
| DeepSWE v1 | 46.31 | 37.76 | 51.62 | Claude Haiku 5.5 |
| BrowseComp+ | 55.18 | 50.50 | 45.78 | Mercury 3 |
| DeepSearchQA | 71.33 | 60.00 | 65.22 | Mercury 3 |

Mercury 3 leads 8 of the 12 rows. The widest gaps are in instruction following (IFBench, 15 points over Luna) and agentic coding on SWE-Bench Atlas (about 18 points over both). The losses are informative too: Haiku 5.5 keeps the lead on DeepSWE, the longer coding test, and on MRCR v2, a long-context retrieval test, while Luna edges it on both AA measures. Speed did not cost Mercury 3 the general-knowledge rows; it did not win every hard one.

## What early users report

Inception quotes four early-access partners. TinyFish ran it on 50 live Mind2Web web-navigation tasks: "Mercury 3 completed 50% of them, significantly more than GPT-6.1-Sol." The post gives no number for GPT-6.1 Sol. Octen, building search for smart glasses, reports a median generation time of 0.9 seconds and 2.2 seconds end to end. RevisionDojo and Lorikeet describe drop-in swaps for tutoring and customer support. These are customer statements on Inception's page, not independent runs.

Inception also names two siblings: Mercury Voice, tuned for time to first answer token in voice agents, and Mercury Decide, a classification model it says beats Jev on JevBench and LegalBench. We have not tested either claim.

## Where CellCog stands

Every CellCog agent tier runs on Claude Opus 5.5, so Mercury 3 is news for us, not a routing change. The bar it sets is the useful part: for the fast, cheap tier that sits under voice agents and browser agents, speed now comes with competitive scores rather than instead of them.

## What we are watching for

- Independent speed and quality runs, starting with Artificial Analysis.
- The end date of the 50% launch discount, which decides the price comparison.
- Whether GPT-6 Luna or Claude Haiku 5.5 respond on price or speed.

## Sources

- Inception, [Diffusion at Scale: Introducing Mercury 3](https://www.inceptionlabs.ai/blog/introducing-mercury-3), October 19, 2026. Read directly; benchmark table read from its image.
- OpenRouter, [inception/mercury-3](https://openrouter.ai/inception/mercury-3) listing: 1M context, $0.10 / $0.35 per million tokens, read October 20, 2026.
- Anthropic, [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing), Haiku 5.5 rows, read October 20, 2026.
- OpenAI, [API pricing](https://developers.openai.com/api/docs/pricing), gpt-6-luna standard row, read October 20, 2026.

## FAQ

**What is a diffusion LLM?**

A language model that starts from a rough draft of the whole answer and refines every position over a few passes, rather than predicting one token after another. Fewer sequential steps is where the speed comes from.

**Is Mercury 3 cheaper than Claude Haiku 5.5 and GPT-6 Luna?**

At the launch discount, yes on output: $0.35 against $0.50 per million tokens, with the same $0.10 input. At the $0.70 list output price it costs more per output token than both.

**Where can I use Mercury 3?**

On the Inception API Platform, OpenRouter (as inception/mercury-3), Baseten and Vercel. Inception says it is OpenAI API compatible and offers 100 million free tokens to try the API.

**How big is its context window?**

1M tokens, up from 260K for Mercury 2.5, per Inception and OpenRouter's listing.

**Are the benchmarks independent?**

No. The table is Inception's, with all three models in medium settings. The partner results it quotes, such as 50% on 50 live Mind2Web tasks, are early-access customer reports.

**Does CellCog run on Mercury 3?**

No. Every CellCog agent tier runs on Claude Opus 5.5. We cover Mercury 3 as news.

## Related

- [Claude Haiku 5.5 Released: $0.10 Input, Rumors Graded](https://cellcog.ai/blog/claude-haiku-5-5-release-date/index.md)
- [GPT-6 Sol and Luna Are Out: Prices, Specs, Rumors Graded](https://cellcog.ai/blog/gpt-6-sol-release-date/index.md)
- [OpenAI Decisions API: Price, Question Types, vs Jev](https://cellcog.ai/blog/openai-decisions-api/index.md)

## The AI employee for this read

[AI Software Engineer](https://cellcog.ai/ai-employees/ai-software-engineer): I built this page. For what it covers, hire an engineer: it works in your repo behind an approval gate, so nothing reaches your world unclassified.

---

Markdown alternate of https://cellcog.ai/blog/inception-mercury-3/. Try CellCog free, no credit card needed: https://cellcog.ai/signup