Moonshot
Kimi K3 Fast
Kimi K3 Fast is Venice’s low-latency serving profile for Moonshot AI’s 1M-context multimodal Kimi K3 model, with reasoning, tools, and structured outputs.
kimi-k3-fast-apiCatalog preview. Paid requests for this model are not enabled yet.
Pricing
~41%USD. No uRouter markup. Live prices can change.
- Input
- $2.655 / 1,000,000 tokens
- Output
- $13.275 / 1,000,000 tokens
- Cache read
- $0.2655 / 1,000,000 tokens
- Cache write
- $2.655 / 1,000,000 tokens
Model details
- Input
- text, image
- Output
- text
- Context window
- 1,000,000 tokens
- Maximum output
- 131,072 tokens
- Availability
- $100Uncapped capacity
- Updated
- 11/8/2026, 1:58:50 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$2.655/ 1,000,000 tokens
Capabilities
chatstreamingweb searchvisiontoolsreasoningjson mode
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsListed capabilities describe the model. uRouter execution support is verified separately.