# MarkTechPost — Inception Releases Mercury 3 Diffusion LLM at 1,068 Tokens per Second

- Company: MarkTechPost (marktechpost.com)
- Announced: 2026-10-20T03:32:43+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.marktechpost.com/2026/10/19/inception-mercury-3-diffusion-llm/
- Record: https://forck.live/items/24936-inception-releases-mercury-3-diffusion-llm-at-1-068-tokens-per-second
- Subject: Reporting
- Models affected: Mercury 3, Mercury 1, Mercury 2, Mercury 2.5, GPT-6 Luna, Claude Haiku 5.5, Mercury Voice, Mercury Decide
- Context window: 1M-token context window
- Pricing: Price, $/1M in / out: $0.20 / $0.70 list ($0.10 / $0.35 launch); Cached input is 90% off

Inception released Mercury 3, a diffusion language model that writes answers in parallel rather than token by token, reporting 1,068 tokens per second on NVIDIA GPUs and a 1M-token context window. The company says Mercury 3 is its fourth Mercury release and more than 40x larger than Mercury 1, with average quality across standard benchmarks rising about 3x between the two models while speed stayed above 1,000 tokens per second. On Inception's own benchmark table, run at medium settings, Mercury 3 leads GPT-6 Luna and Claude Haiku 5.5 on 8 of 12 tests, including SWE-Bench Atlas at 51.08 against 33.33 and 32.26, and IFBench at 76.84. It loses to Haiku 5.5 on DeepSWE v1 (46.31 versus 51.62) and MRCR v2 (75.50 versus 78.40), leaving long-context retrieval and longer coding tasks as weak spots. Mercury 3 is available through the Inception API Platform, OpenRouter, Baseten and Vercel, with an OpenAI-compatible API using the model string mercury-3 and a reasoning_effort parameter. List pricing is $0.20 per 1M input and $0.70 per 1M output tokens, discounted 50% at launch to $0.10 and $0.35, with cached input 90% off and 100M free tokens for new accounts. Inception also ships two siblings: Mercury Voice, aimed at time to first answer token in voice agents, and Mercury Decide, a classification model.

## Evidence

Verbatim from https://www.marktechpost.com/2026/10/19/inception-mercury-3-diffusion-llm/:

> List pricing is $0.20 per 1M input and $0.70 per 1M output tokens. At launch it is 50% off: $0.10 and $0.35. Cached input is 90% off. New accounts get 100M free tokens.

---

Record: https://forck.live/items/24936-inception-releases-mercury-3-diffusion-llm-at-1-068-tokens-per-second
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md