Back to Model
M

Mercury 3

Model Oct 19, 2026

Inception's hosted diffusion language model, with a million-token context window and vendor-reported generation speed above 1,000 tokens per second.

Visit primary link 2 sources attached
Inception's Mercury 3 comparison table lists vendor-reported speed, launch pricing and benchmark results against GPT-6 Luna and Claude Haiku 5.5, including tests led by other models.
Inception's October 19 launch comparison, with the complete table preserved. These are vendor-reported results and introductory prices, not independently reproduced AITrending measurements or a universal model ranking. Source: Inception / Mercury 3 launch announcement
ai-agents

What happened lately

Mercury 3 timeline

Inception announced Mercury 3 on October 19, 2026, with a one-million-token context window and hosted API access. The company reports 1,068 output tokens per second on NVIDIA GPUs and compares its quality with speed-oriented models from OpenAI and Anthropic. Those speed and benchmark figures are vendor claims, not independently reproduced AITrending measurements.

The quick start uses the model identifier mercury-3 at an OpenAI-compatible chat-completions endpoint. Users create an Inception account and API key; the documentation advertises 100 million introductory free tokens. The announcement lists standard pricing of $0.20 per million input tokens and $0.70 per million output tokens, with a 50% launch discount. Availability through a hosted API does not establish that model weights are downloadable or that every workload reaches the advertised generation speed.