Post-Cutoff
Search For AI agents

InceptionMercury familyCurrentReasoning modelReleased 19 Oct 2026

Mercury 3

Fast, cheap model for agent sub-calls, search pipelines and voice, where latency matters more than peak intelligence.

Model idmercury-3

Price$0.20 in, $0.70 out per 1M tokens

Checked20 October 2026

No published training cutoff

At least2events since its release on 19 October 2026

0 historic, 0 major. 1 day of news.

Inception doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

How to call it

5 ways to use Mercury 3, with the model id each provider expects.

Providers, model ids, endpoints and docs for Mercury 3
ProviderModel idEndpointDocs
Inception API (OpenAI-compatible) mercury-3 https://api.inceptionlabs.ai/v1/chat/completions docs.inceptionlabs.ai
OpenRouter inception/mercury-3 openrouter.ai
Baseten baseten.co
Vercel vercel.com
Web app chat.inceptionlabs.ai

Pricing

Prices for Mercury 3
Input$0.20 per 1M tokens
Output$0.70 per 1M tokens

As published: “per 1M tokens (list price; 50% launch discount brings it to $0.10 / $0.35, end date not stated; cached input $0.02, $0.01 at launch)”.

Source: docs.inceptionlabs.ai, checked 20 October 2026.

Specs

Input
Text
Output
Text
Context window
1,000,000 tokens
Max output
131,072 tokens
Open weights
No
Licence
Proprietary
Training cutoff
Not published
Released
19 October 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Diffusion LLM with 1M-token context

    Generates and refines many tokens in parallel; Inception claims 1,068 tokens/s on Nvidia GPUs, 4–8x faster than GPT-6 Luna and Claude Haiku 5.5, with a 1M-token context (up from 260K in Mercury 2.5).

    Source: inceptionlabs.ai

  • Reasoning effort levels and tool calling

    instant, low, medium and high reasoning effort; tool calling and structured outputs; temperature 0.5–1.0 (Inception docs).

    Source: docs.inceptionlabs.ai

Notes

Inception says it beats GPT-6 Luna and Claude Haiku 5.5 on “a range of benchmarks” but published no scores; independent numbers not yet available on Oct 20. OpenRouter lists 1M context at $0.10/$0.35 (launch price). 100M free API tokens for new accounts.

Sources: Inception blog · Inception docs · The Deep View