[Late catch] Inception Mercury 3: a 1,000-tokens-per-second diffusion LLM with 1M context
What is it?
Mercury 3 is Inception's diffusion LLM. Instead of writing one token at a time, a diffusion LLM drafts the whole answer and refines it over several passes, which makes it fast. Context grows from 260K tokens in Mercury 2.5 to 1M, and the API is OpenAI-compatible, so existing clients only need a new base URL and model name. It's available on the Inception API, OpenRouter, Baseten, and Vercel.
curl https://api.inceptionlabs.ai/v1/chat/completions -H "Authorization: Bearer $INCEPTION_API_KEY" -H "Content-Type: application/json" -d '{"model":"mercury-3","messages":[{"role":"user","content":"Hello"}]}'Why does it matter?
Inception reports 1,068 tokens per second on NVIDIA GPUsVendor claim and says it's 4–8x fasterVendor claim than GPT-6 Luna and Claude Haiku 5.5. Pricing is $0.20 per million input tokens and $0.70 per million outputVendor claim, half that during the launch promotion. For latency-sensitive work like classification, extraction, and autocomplete, it's a candidate to replace small autoregressive models. Inception hasn't published a named benchmark table, though, so test quality yourself.
Maturity
GAIt's a commercial API you can use today on several platforms. Weights aren't released, and there are no independent measurements of its performance yet.
How to track it
- Independent numbers: see whether Artificial Analysis and others post an intelligence score and measured speed for Mercury 3.
- Pricing: check Inception's pricing page and OpenRouter rates for when the 50% launch discount ends.
- Older models: Mercury 2 and 2.5 are closed to new sign-ups, so watch Inception's docs for when existing customers lose access.