databricks/databricks-kimi-k3
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsdatabricks/databricks-kimi-k3
AI model
- API mode
- Chat*
- Maximum output
- 1,048,576 tokens*
No matched benchmark results are available for this entry yet.
Run it locally
Capabilities
- Maximum input
- 1,000,000 tokens*
- Maximum output
- 1,048,576 tokens*
- Reasoning
- Yes*
- Tool calling
- Yes*
- API mode
- Chat*
- Image input
- Yes*
- Prompt caching
- Yes*
- Tool choice
- Yes*
Input modalities
- text*
- image*
Output modalities
- text*
System configuration
Detailed specifications
Specifications · 20 fields
- cache creation input token cost
- 2.99999e-6*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- cache read input token cost
- 3.0002e-7*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input cost per token
- 2.99999e-6*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- input dbu cost per token
- 4.2857e-5*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- litellm provider
- databricks*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max input tokens
- 1,000,000*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max output tokens
- 1,048,576*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- max tokens
- 1,048,576*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- metadata
- notes
- Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference.*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- mode
- chat*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token
- 1.500002e-5*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output dbu cost per token
- 0.000214286*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported modalities
- text*
- image*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported output modalities
- text*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports function calling
- Yes*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports prompt caching
- Yes*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports reasoning
- Yes*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports tool choice
- Yes*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports vision
- Yes*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- token count framing
- 100*
Scope and conditions
- native_context
- provider
- databricks*
- mode
- chat*
- full_native_model_id
- databricks/databricks-kimi-k3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
0 selected Compare 0
* Provisional data