Inception: Mercury
inception/mercury
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude...
Prompt $/1M
$0.250
Completion $/1M
$0.750
Context
128,000 tok
Best provider
26 tok/s · Inception
Specs
- Model id
- inception/mercury
- Display name
- Inception: Mercury
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 128,000
- Max completion
- 32,000
- Prompt $/1M
- $0.250
- Completion $/1M
- $0.750
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Inceptionfastest | 26 |
| inceptionfastest | — |