Mercury 2 · azureml-inceptionlabs v1
State-of-the-art diffusion based reasoning model.
azureFoundry/azureml-inceptionlabs/Mercury-2@1
State-of-the-art diffusion based reasoning model.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 128000
- Max output · tokens
- 50000
- Knowledge cutoff
- 2026-02
- Capabilities
- reasoning, toolCalling
Provider specifications & access
1–1 / 1
- source model id
- azureml-inceptionlabs/Mercury-2@1
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 128000
- max output tokens
- 50000
Source specification observations
1–3 / 3
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 50000
- normalized value
- 50000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- February 2026
- normalized value
- 2026-02
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models