All models

Kimi K3.1 Pro

New Launched on IteraCompute

已上线

Moonshot AI

moonshotai/kimi-k3.1-pro
Tool calling
支持工具调用 · 支持
Reasoning
支持推理 · 支持
Vision
支持视觉 · 支持
Streaming
支持流式输出 · 支持
JSON mode
支持JSON 模式 · 支持

USD / 1M tokens

Input
$1.60
Cache read
$0.16
Cache write
$1.60
Output
$8.00
Context
896K
Max output
128K
Precision
官方精度
Price checked

Overview

Kimi K3.1 Pro accepts text and images and generates text for conversation, document work, structured responses and tool-assisted applications. Clients use the public Model ID through the configured Qianfan route.

Version
qianfan-vl-v1.1
Input / output
text, image / text
Endpoint
/v1/chat/completions, /v1/responses, /v1/messages

API protocols and integration

Base URL · OpenAI SDK
https://api.iteracompute.com/v1
鉴权
Authorization: Bearer ITERACOMPUTE_API_KEY

按接口选择请求字段、读取结果和流式结束标记;下表是协议格式,实际能力与验证范围以本模型说明为准。

客户接口本模型状态输入 / 输出预算返回结果SSE 结束标记
OpenAI Chat Completions
POST /v1/chat/completions
已列入模型资料messages
max_tokens
choices[0].message.content[DONE]
OpenAI Responses
POST /v1/responses
已列入模型资料input
max_output_tokens
output[] (SDK: output_text)response.completed
Anthropic Messages
POST /v1/messages
已列入模型资料messages; system (top-level)
max_tokens (required)
content[]message_stop

Messages SDK 的 Base URL 使用 https://api.iteracompute.com;max_tokens 为必填。其他协议字段请勿直接套用。

查看文档
LLMs.txt · 复制给 AI 编程助手

包含此模型的 ID、接口格式和参数约束。复制前请核对本页验证范围与当前价格。

LLMs.txt
# IteraCompute · moonshotai/kimi-k3.1-pro

Model ID: moonshotai/kimi-k3.1-pro
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json

仅使用下列客户接口;不同协议的请求和响应结构不可混用。接口声明不等于每项能力均已实测。

## Chat Completions
POST https://api.iteracompute.com/v1/chat/completions
Input: messages
Output budget: max_tokens
Read result: choices[0].message.content
SSE completion: [DONE]
Docs: https://iteracompute.com/docs.html#api-reference

## Responses
POST https://api.iteracompute.com/v1/responses
Input: input
Output budget: max_output_tokens
Read result: output[] (SDK: output_text)
SSE completion: response.completed
Docs: https://iteracompute.com/docs.html#responses-api

## Messages
POST https://api.iteracompute.com/v1/messages
Input: messages; system (top-level)
Output budget: max_tokens (required)
Read result: content[]
SSE completion: message_stop
Docs: https://iteracompute.com/docs.html#anthropic-messages

## Parameters
配置范围和参数可接收性不等于模型语义能力验收;未公布的默认值不要自行补全。
Parameter revision: 1e481701fe324a5a4da4261e0d67b94138fde98cf01a971d1340decae1a253b6
Context tokens: 917504
Maximum output tokens: 131072
Capability tools: configured enabled (see verification scope)
Capability vision: configured enabled (see verification scope)
Capability json_mode: configured enabled (see verification scope)
Capability reasoning: configured enabled (see verification scope)
Capability streaming: configured enabled (see verification scope)
Capability image_editing: disabled
Capability image_generation: disabled
- max_tokens: integer; accepted; min=1; max=131072; default=未公布. 输出 Token 预算;适用时包含推理 Token。用于 Chat Completions / Messages。
- cache_control: object; unsupported; min=unknown; max=unknown; default=not applicable. 消息、内容块、系统块或工具定义上的缓存策略。
- prompt_cache_options: object; unsupported; min=unknown; max=unknown; default=not applicable. 请求级提示缓存策略;自定义设置须完成对应计费验收。
- prompt_cache_retention: string; unsupported; min=unknown; max=unknown; default=not applicable. 提示缓存保留时长;允许值以模型配置为准。
- prompt_cache_breakpoint: object; unsupported; min=unknown; max=unknown; default=not applicable. 输入项或内容块上的显式提示缓存断点。

## Chat Completions example · JSON body
```json
{
  "model": "moonshotai/kimi-k3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256
}
```

## Responses example · JSON body
```json
{
  "model": "moonshotai/kimi-k3.1-pro",
  "input": "Reply OK",
  "max_output_tokens": 256
}
```

## Messages example · JSON body
```json
{
  "model": "moonshotai/kimi-k3.1-pro",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ]
}
```

## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.

打开纯文本

API parameters

  • Client Model ID: moonshotai/kimi-k3.1-pro; upstream model: qianfan-vl-v1.1.
  • Chat Completions, Responses and Messages are available customer protocols. Tool use, JSON, vision and reasoning coverage is stated in the verification scope.
  • Retail USD per million tokens: input 1.60, cache read 0.16, default 5-minute cache write 1.60, output 8.00: 80% of the corresponding official rates.
  • max_tokens is an integer from 1 to 131,072; Responses uses max_output_tokens. Output budgets include applicable reasoning tokens.

以下为当前线路接受的参数与取值范围,账户额度和上下文限制同时适用。参数可接收不代表相关模型能力已经完成验证。

工具调用
支持
推理
支持
视觉
支持
流式输出
支持
JSON 模式
支持
图像编辑
不支持
图像生成
不支持

参数与取值

点击参数名即可复制;表格可横向滚动查看全部列。用途栏标明协议差异,不能将同名字段视为跨接口通用。

参数类型接收状态取值范围用途 / 协议
整数可接收[1, 131072]输出 Token 预算;适用时包含推理 Token。用于 Chat Completions / Messages。
对象不支持—消息、内容块、系统块或工具定义上的缓存策略。
对象不支持—请求级提示缓存策略;自定义设置须完成对应计费验收。
字符串不支持—提示缓存保留时长;允许值以模型配置为准。
对象不支持—输入项或内容块上的显式提示缓存断点。

当前配置调用示例

POST /v1/chat/completions

Chat Completions 请求参数
{
  "model": "moonshotai/kimi-k3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256
}

参数版本:1e481701fe32

API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/kimi-k3.1-pro",
    messages=[
      {
        "role": "user",
        "content": "Reply OK"
      }
    ],
    max_tokens=256,
)
print(response.choices[0].message.content)

Pricing

USD per million tokens. — means unknown. Account and subscription limits still apply.

Input$1.60
Cache read$0.16
Cache write$1.60
Output$8.00
Version / Model ID
moonshotai/kimi-k3.1-proqianfan-vl-v1.1
Context
896K
Precision
官方精度
Price checked
Verification scope and sources
View verification scope and sources

2026-11-13 · Verified with short live requests: default reasoning and reasoning-token usage, tools, JSON, red/blue image recognition, three text protocols with streaming/usage, parameter boundaries and billing. No full-context, cache-hit/write or latency guarantee.

完整 Token 价格

单位:美元 / 百万 Token。— 表示未知价格。上下文区间包含缓存读取和写入 Token,区间为左开右闭 (起点, 终点]。

计费项目本站销售价官方参考价
输入$1.6$2
缓存读取$0.16$0.2
缓存写入$1.6$2
输出$8$10
Revision: a4f0bda7cf4e

Vendor-documented context window · 1,048,576 tokens · Maximum output · 1,048,576 tokens ·

Cost calculator

USD · Estimate
Calculation mode
Advanced token usage

Input includes cache reads and writes; these portions must not overlap. Output already includes reasoning; enter reasoning as a subset, never add it twice. Count agent steps and retries as requests.

Estimated monthly cost

—USD

Kimi K3.1 Pro

Cache hits and capacity are not guaranteed.

Cost breakdown
Uncached input
—
Cache read
—
Cache writes (5m + 1h)
—
Output (including reasoning)
—

Usage limits

  • Text output only; image generation, audio and video are outside this route.
  • Configured input limit: 917,504 tokens; output limit: 131,072 tokens. Low-cost tests do not certify full-context accuracy. Account and request limits also apply.
  • This Qianfan route returns reasoning content and reasoning-token usage by default. Effort selection is not exposed; an explicit reasoning_effort=low request is rejected upstream.
  • Custom cache lifetimes and explicit cache breakpoints are disabled until billing acceptance; default implicit caching follows the published rates.

Use cases

Text drafting, summarization and questions

Structured JSON responses and tool calls

Image interpretation and text reasoning

Integration tools and guides

FAQ

How do I call Kimi K3.1 Pro?

Use Model ID moonshotai/kimi-k3.1-pro and the native fields in this page's API examples. Declared endpoints: /v1/chat/completions, /v1/responses, /v1/messages.

How is usage priced?

Use the current prices and billing units. Missing prices remain unknown, not free. The calculator uses native Gateway quotes; an estimate is not a bill.

Which parameters and limits apply?

Check the current parameter table and usage limits. Budget fields differ by protocol. Configured limits do not establish full-window quality or guarantee a maximum-length output.

New arrivals

Explore the models selected for New Arrivals, with API pricing, supported capabilities and integration guides.

View new arrivals
GoogleNew

Gemini 4 Hydrogen

gemini/gemini-4-hydrogen

Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.

Launched on IteraCompute

Input
$1.50
Output
$7.50

USD / 1M tokens

OpenAINew

GPT-6.2 Astra

openai/gpt-6.2-astra

OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.

Launched on IteraCompute

Input
$8.00
Output
$40.00

USD / 1M tokens

OpenAINew

GPT-6.2 Sol

openai/gpt-6.2-sol

OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.

Launched on IteraCompute

Input
$2.00
Output
$10.00

USD / 1M tokens