Mercury 3
Model Information
| Slug | mercury-3 |
|---|---|
| LLMs.txt | View |
| Release Date | October 19, 2026 New |
| GPQA | 0.8923 |
Organization
| Name | Inception |
|---|
Model Description
Mercury 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 as search agents, voice pipelines, and coding subagents. Its distinguishing trait is speed: more than 40x larger than the first Mercury model while generating at the same throughput, because it produces and refines tokens in parallel rather than one at a time.
Available at 17 Providers
| Provider | Type | Model Name | Original Model | Input ($/1M) | Output ($/1M) | Free | Actions | |
|---|---|---|---|---|---|---|---|---|
|
Routstr |
P2P
|
Mercury 3
|
mercury-3
|
$0.045 | $0.16 | ||
|
Cline |
Code
|
Inception: Mercury 3
|
inception/mercury-3
|
$0.10 | $0.35 | ||
|
Glama |
mercury-3
|
inception/mercury-3
|
$0.10 | $0.35 | |||
|
Nous Research |
Inception: Mercury 3
|
inception/mercury-3
|
$0.10 | $0.35 | |||
|
OpenRouter |
Chat
Code
|
Mercury 3
|
inception/mercury-3
|
$0.10 | $0.35 | ||
|
UsePod |
P2P
|
mercury-3
|
mercury-3
|
$0.10 | $0.35 | ||
|
ValorGPT |
IN
|
inception-mercury-3
|
$0.10 | $0.35 | |||
|
Vercel AI Gateway |
Mercury 3
|
inception/mercury-3
|
$0.10 | $0.35 | |||
|
Nano-GPT |
Chat
Code
|
Mercury 3
|
inception/mercury-3
|
$0.10 | $0.35 | ||
|
Mordiem |
Mercury 3
|
mercury-3
|
$0.10 | $0.35 | |||
|
Venice |
Mercury 3
|
mercury-3
|
$0.10 | $0.35 | |||
|
Inception |
Mercury 3
|
mercury-3
|
$0.10 | $0.35 | |||
|
Kilo Code |
Code
|
Inception: Mercury 3
|
inception/mercury-3
|
$0.20 | $0.70 | ||
|
WaveSpeed AI |
Chat
Code
|
mercury-3
|
inception/mercury-3
|
$0.20 | $0.70 | ||
|
Concentrate AI |
Mercury 3
|
mercury-3
|
- | - | |||
|
Krater |
Inception: Mercury 3
|
mercury-3
|
- | - | |||
|
Writingmate |
Chat
Code
|
Inception: Mercury 3
|
inception/mercury-3
|
- | - |