Amazon Bedrock adds India in-region inference for Kimi K3
Understand this story
Amazon Bedrock now supports India in-region inference for Kimi K3. When users call it through the in.moonshotai.kimi-k3 inference profile, request processing is restricted to the Mumbai and Hyderabad regions to meet strict data residency requirements; previously the model was available only with global and US in-region inference. Billing is per token. Latency-insensitive use cases can choose the flex tier, billed at 50% of the default standard price; latency-sensitive use cases can choose the priority tier, paying a higher price for higher queue priority. Model invocation logging is optional and can include prompts and outputs.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogIntroducing India-based inference for Kimi K3 on Amazon Bedrock
Amazon Bedrock now supports in-country inference in India for Moonshot AI's multi-modal, open-weight Kimi K3 model via the in.moonshotai.kimi-k3 geographic inference profile, processing requests in the Mumbai and Hyderabad Regions for workloads with strict data residency requirements. The post explains global versus India inference profiles and walks through an example of OCR and document understanding for Indic-language documents, including structured extraction and follow-up questions in code-mixed Hinglish. It also covers prompt caching, service tiers, and CloudWatch monitoring, citing Ultrahuman's report of 80 percent lower LLM costs and 85 percent faster multi-turn chats with prompt caching.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 02:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.