Kimi K2.5
moonshotai/kimi-k2.5
- context
- 262K
- modalities
- text, image → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Low cost
Overview
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Providers
- Amazon BedrockView Amazon Bedrock
- AtlasCloudView AtlasCloud
- NovitaView Novita
- SiliconFlowView SiliconFlow
- VeniceView Venice
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Amazon Bedrockamazon-bedrock | $0.60 | $3.00 |
| Amazon Bedrockamazon-bedrock/us-east-2 | $0.60 | $3.00 |
| AtlasCloud | $0.49 | $2.50 |
| Novita | $0.57 | $2.85 |
| SiliconFlow | $0.50 | $2.50 |
| Venice | $0.532 | $3.325 |
Amazon Bedrock
amazon-bedrock
- input / 1M
- $0.60
- output / 1M
- $3.00
Amazon Bedrock
amazon-bedrock/us-east-2
- input / 1M
- $0.60
- output / 1M
- $3.00
AtlasCloud
- input / 1M
- $0.49
- output / 1M
- $2.50
Novita
- input / 1M
- $0.57
- output / 1M
- $2.85
SiliconFlow
- input / 1M
- $0.50
- output / 1M
- $2.50
Venice
- input / 1M
- $0.532
- output / 1M
- $3.325
Use this model
through Nautili
Route requests to Kimi K2.5 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.