Inception · Inception: Mercury
Inception: Mercury 3
CONFIRMEDMercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
1MKontext
131KMax. Output
TextInput
TextOutput
$0.1Input / 1M
$0.35Output / 1M
JaTools
JaReasoning
JaStructured
Benchmarks werden ergänzt, sobald Werte vorliegen.
Inception · Inception: Mercury
Inception: Mercury 2.5
CONFIRMEDMercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
260KKontext
66KMax. Output
TextInput
TextOutput
$0.04Input / 1M
$0.15Output / 1M
JaTools
JaReasoning
JaStructured
Benchmarks werden ergänzt, sobald Werte vorliegen.
Inception · Inception: Mercury
Inception: Mercury 2
CONFIRMEDMercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
128KKontext
50KMax. Output
TextInput
TextOutput
$0.25Input / 1M
$0.75Output / 1M
JaTools
JaReasoning
JaStructured
Benchmarks werden ergänzt, sobald Werte vorliegen.