AWS Makes Kimi K3.1 Pro Highspeed Available on Amazon Bedrock

Amazon Web Services made Moonshot AI’s Kimi K3.1 Pro Highspeed available on Amazon Bedrock on November 10, 2026, offering a 1-million-token context window through global, US and India inference profiles. Moonshot AI reports that the Highspeed variant generates output two to three times faster than K3.1 Pro.

The underlying model’s launch date was November 4, 2026, ahead of this Bedrock deployment. K3.1 Pro is a post-trained version of Kimi K3, retaining the 3T-class open-weight architecture and context window while using substantially more post-training compute. Moonshot AI says the additional training targets long-horizon agentic work and fewer factual errors, with improvements in financial modeling, office documents, and coding for game engines, 3D scenes and computer-aided design scripts.

In agentic coding, a single task can require many sequential model calls: reading files, planning a change, editing code, running tests and fixing failures. A higher output-token rate can shorten the generation portion of each step. Existing Kimi K3 implementations on Bedrock can switch by changing the model ID, while the new model supports tool calling, structured output, configurable reasoning, image input and streaming through the same endpoint and APIs. AWS also demonstrates OpenCode, an open-source terminal coding agent, connected through Chat Completions and a Bedrock API key.

Access and Data Residency

Developers can call the model through the OpenAI-compatible Chat Completions and Responses APIs, or Bedrock’s Converse and Invoke APIs. AWS recommends Chat Completions. The global cross-Region inference profile routes requests to any supported commercial AWS Region, while the US and India profiles constrain routing to their respective geographies for data-residency requirements. India requests are routed between Mumbai and Hyderabad.

AWS says inference data stays within the AWS data boundary, is not shared with Moonshot AI and is not used to train the model. Zero data retention is always enabled for inference requests, and AWS operators cannot view prompts or completions during inference.

Pricing and Cost Controls

Standard-tier rates depend on the routing profile. All prices below are per 1 million tokens:

On the Bedrock pricing page, the preceding Kimi K3 is listed at $3.00 per million input tokens and $15.00 per million output tokens for Global Standard inference. The new model therefore carries higher input and output rates, although its global cache-read rate is lower than K3’s $0.30 per million tokens.

Flex offers inference at half the Standard rate in exchange for potentially longer response times, while Priority carries a 75% premium. The tier is selectable per request, so an application can use Standard for ordinary traffic, Priority for latency-critical calls and Flex for evaluations, summarization or background agent work.

Explicit prompt caching addresses repeated context such as system instructions, tool definitions and repository conventions. Each breakpoint must follow at least 256 tokens of stable content. The feature works on Responses, Chat Completions and Invoke, but not Converse. Cache reads are discounted and do not count toward the input tokens-per-minute quota, while writes cost more than standard input.

Reasoning and Compatibility Limits

The model card supports reasoning settings of none, low, medium, high, xhigh and max, with max used by default. Setting none turns reasoning off for a request. Lower effort can reduce latency and token consumption in exchange for task performance, making the default an important consideration for cost-sensitive workloads.

Converse has additional constraints beyond its lack of explicit caching. It can fail with an internal server error when reasoning content from earlier turns is included in a multi-turn request, affecting frameworks such as LangChain and Strands Agents in their default configurations. AWS recommends removing prior reasoning blocks for multi-turn Converse requests. Converse also rejects attached PDF and HTML documents, and Bedrock does not support video inputs for this model.

Each output token also consumes 10 tokens from the applicable account quota on the bedrock-runtime endpoint, a separate capacity consideration from the per-token bill.

For existing K3 users, switching requires little code change, but the operating trade-off extends beyond compatibility. The potential gain is faster completion of sequential agent work; the counterweights are higher input and output prices, reasoning-driven token use and quota consumption. Flex, caching and effort settings are the controls AWS provides to balance those demands.