Kimi-K2.5 · azureml-moonshotai v1
Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.
azureFoundry/azureml-moonshotai/Kimi-K2.5@1
Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.
Specifications & capabilities
- Input
- text, image
- Output
- text
- Context window · tokens
- 262144
- Max input · tokens
- 262144
- Max output · tokens
- 262144
- Capabilities
- multimodal, reasoning, visionInput
Provider specifications & access
1–1 / 1
- source model id
- azureml-moonshotai/Kimi-K2.5@1
- hosting
- foundry-managed
- license
- other
- context length
- 262144
- max input tokens
- 262144
- max output tokens
- 262144
Source specification observations
1–3 / 3
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_input_tokens
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models