AI Devtools Radar

Kimi API

模型 APIplatform.moonshot.ai14 条已发布变化

2 个来源在监控

变化时间线

featurehigh

K3 模型 Batch API 推理现已可用，价格优惠 60%

开发者现在可以使用 Batch API 来处理 K3 模型的非实时任务，成本节省 40%（标准价格的 60%），从而能够更经济地处理大规模工作负载。

证据
+Batch API Inference: kimi-k3.1-pro and kimi-k3 support batch inference for large-scale tasks that do not require real-time responses, billed at 60% of the standard price.

platform.moonshot.ai

api

示例中的默认模型从 kimi-k3 更改为 kimi-k3.1-pro

所有代码示例现在默认使用新的 K3.1 Pro 模型，如果开发者想使用旧版本，需要显式指定替代模型。

证据
−model="kimi-k3"
+model="kimi-k3.1-pro"

platform.moonshot.ai

other

上下文缓存术语从 'Cache Write' 更新为自动计费模式

文档澄清了上下文缓存对重复请求前缀自动启用（默认 TTL 为 5m），简化了计费模式说明。

证据
−Note: Cache Write refers to the cost of writing request prefixes into the context cache. The Kimi API automatically caches repeated request prefixes, and cache entries come in two time-to-live (TTL) tiers — 5min and 1h. If no TTL is specified, the 5min tier applies by default.
+Note: The Kimi API automatically enables context caching billing for repeated request prefixes, with a default TTL (time-to-live) of 5m.

platform.moonshot.ai

featurehigh

K3 series 上下文窗口扩展至 1,048,576 tokens

K3 series 用户现在拥有更大的上下文窗口，可以在不截断的情况下处理更长的文档和对话。

证据
+All K3 series models support a 1,048,576-token context window.

platform.moonshot.ai · 另有 1 个来源报告了同一变化

deprecationhigh

K2 series 模型已弃用，采取分阶段退休计划

从 2026 年 10 月 31 日起，K2 series 对新用户将不可用，并在 2026 年 12 月 31 日完全停用。现有用户必须迁移到较新的模型。

证据
+starting October 31, 2026, K2 series models will no longer be available to newly registered users; existing users are not affected. We plan to retire all K2 series models by the end of December 2026, please prepare your migration in advance.

platform.moonshot.ai · 另有 1 个来源报告了同一变化

api

API 文档已明确说明具体的端点命名和品牌变更

与 Kimi API 集成的开发者将看到 OpenAI 兼容端点和 Anthropic 兼容端点的官方命名，以及更新的产品品牌参考。

证据
−Kimi API lets you interact with Kimi models and is compatible with both the OpenAI and Anthropic API formats.
+Kimi API Platform provides access to Kimi models through the OpenAI-compatible Responses API and the Anthropic-compatible Messages API.

platform.moonshot.ai

feature

Kimi Code 和 Codex 已添加到 Kimi K3 用例列表中（与 Claude Code 一起）

用户现已了解到 Kimi K3 可用于 Kimi Code 和 Codex 编程智能体场景，将 Kimi 自有的智能体解决方案确立为主要用例。

证据
−It is well suited for programming agent scenarios such as Claude Code, as well as knowledge work and deep reasoning.
+It is well suited for programming agent scenarios such as Kimi Code, Codex, and Claude Code, as well as knowledge work and deep reasoning.

platform.moonshot.ai

positioning

现有内容重新归类至 K2 Series Models 类别

澄清原始计费模型（基于输入/输出使用量）特别适用于 K2 Series，将其与新的 K3 Series 缓存模型区分开来。

证据
−Model inference APIs bill both Input and Output based on usage.
+K2 Series Models Model inference APIs bill both Input and Output based on usage.

platform.moonshot.ai

featurehigh

推出 K3 Series Models，配备 context cache 定价结构

用户现在可以使用 K3 Series models，支持自动请求前缀缓存（5min 和 1h TTL 选项），通过以低于常规输入费率的缓存输入费率实现成本节省。

证据
+K3 Series Models Note: Cache Write refers to the cost of writing request prefixes into the context cache. The Kimi API automatically caches repeated request prefixes, and cache entries come in two time-to-live (TTL) tiers — 5min and 1h. If no TTL is specified, the 5min tier applies by default. Input that hits the cache within its lifetime is billed only at the Cached Input Price: each hit automatically refreshes the cache entry's lifetime, with no additional cache write charge.

platform.moonshot.ai

pricinghigh

K3 models 的缓存写入按 TTL 层级单独计费，缓存命中不收费

K3 model 用户通过缓存命中在重复请求上获益于较低成本，缓存写入成本透明，缓存命中仅按降低的缓存输入费率收费。

证据
−Model inference APIs bill both Input and Output based on usage.
+For K3 series models, cache writes are billed separately per TTL tier (5min / 1h); cached input is billed at the cache-hit price only, with no additional cache write charge.

platform.moonshot.ai

pricinghigh

账单方法自 9 月 14 日起改为现金和代金券 50/50 分账

所有未签订合同的用户将以 50% 现金和 50% 代金券的方式扣除账户使用费，而不是之前的方法。当任一余额耗尽时，剩余使用费从另一种余额类型中扣除

证据
+Starting at 00:00 on September 14, account usage on the Kimi API Open Platform (platform.kimi.ai) will be deducted at a uniform ratio of 50% from cash and 50% from vouchers. When either the cash or voucher balance is depleted, all subsequent account usage will be deducted from the remaining balance type.

platform.moonshot.ai

other

从文档中移除对 kimi-k2.5 模型的引用

kimi-k2.5 不再作为替代模型示例被提及。

证据
−To use another model such as kimi-k2.6 or kimi-k2.5, just replace the model field
+To use another model such as kimi-k2.6, just replace the model field

platform.moonshot.ai

apihigh

Kimi API 现在同时支持 Anthropic API 格式和 OpenAI 格式

开发者现在可以将 Kimi 与 Anthropic SDK 和 Claude Code 集成一起使用，兼容性扩展超越 OpenAI 生态。

证据
−Kimi API lets you interact with Kimi models and is compatible with the OpenAI API format.
+Kimi API lets you interact with Kimi models and is compatible with both the OpenAI and Anthropic API formats.

platform.moonshot.ai

deprecationhigh

Moonshot V1 模型系列停用，整个平台日落

使用 Moonshot V1 的开发者需要在 8 月 31 日前迁移到新模型，整个 V1 平台将停止支持。

证据
−Moonshot V1 Classic generation model series; full platform sunset expected on August 31

platform.moonshot.ai