Kimi K3.1 Pro Highspeed

Highspeed is the faster variant of K3.1 Pro: it responds faster and costs more per token. The request contract is the same, with the same /v1/chat/completions endpoint, always-on reasoning, and low/high/max efforts, so switching only requires changing model between kimi-k3.1-pro and kimi-k3.1-pro-highspeed. Choose Highspeed for latency-sensitive interactions and K3.1 Pro when cost matters more, and compare usage and latency on your own tasks. See the model pricing for each rate.

Try low for routine extraction, rewriting, and short answers; high for multi-step analysis; and max for hard reasoning or whole-project coding. reasoning_effort defaults to max and accepts only these three values; there is no medium or none. Higher efforts usually spend more reasoning tokens and take longer, so choose by answer quality and usage.

Reasoning is always on for K3.1 Pro Highspeed, and temperature=1 and top_p=0.95 are fixed. Omit thinking, temperature, and top_p; a request with any other temperature or top_p value returns HTTP 400 and is not billed. To reduce cost, lower reasoning_effort to low first. When migrating from another model, remove these sampling parameters.

Reasoning is billed as output, so the visible answer length does not reflect total output. usage.completion_tokens already includes reasoning tokens; completion_tokens_details.reasoning_tokens is a breakdown, so do not add it twice. max_tokens also counts reasoning, and a very small value can cut the response off before the answer appears.

Send back the complete assistant message returned by the API, including content, reasoning_content, and tool_calls; keeping only the final text loses context. tool_calls are proposals that your application executes. Append a role=tool result whose tool_call_id matches the original call, then request the next turn. tool_choice accepts auto, none, and required; naming a specific function is not supported because reasoning is always on.

response_format.type=json_object returns JSON, but your application still validates the fields. To constrain fields and types, use response_format.type=json_schema with json_schema.schema and strict=true. Parse choices[0].message.content; do not include reasoning_content.

The official model may support image and video understanding, but this HiAPI integration currently exposes text input and text output through Chat Completions only. Do not copy the official image_url, video_url, or Responses examples. Any future input types will appear in this page's capabilities and Playground controls.

Repeated request prefixes are cached automatically with no extra parameter. Cached tokens appear in usage.prompt_tokens_details.cached_tokens and are billed at the cache-read rate; the rest of the input is billed as regular input. Cache hits are not guaranteed; see the model pricing for each rate.