Skip to main content
Chinese AI Tools
ProductsModelsIntegrationsRankingsLatest changes
TopicsAvailability TrackerUse casesSubmit a toolAccount
ZHSearch

Chinese AI Tools

Independent directory for Chinese AI products. Product availability, pricing and terms can change. Verify before commercial use.

Editorial standardsClaim productUpdate infoGet featuredAdvertise

Moonshot AI

Kimi K2 API

Kimi's international developer API for K3, K2.7 Code, K2.6, K2.5, K2 and Moonshot V1 models with OpenAI-compatible access.

Globally availableFull English UIPublic APIPaid

Quick answer

Kimi's developer path is separated through K2.7 Code, K2.6 and the English API platform, so it should be distinct from the consumer assistant and Kimi Code CLI.

Official sitePricingDocumentation
Pricing
Pay-as-you-go API pricing varies by Kimi K2 and Moonshot model
Availability
Globally available
API
Public API
Last checked
2026-08-04
Pricing detailsUse-case fitSource evidence

The Kimi API now exposes Kimi K3 alongside K2.7 Code, K2.6, K2.5, K2 and Moonshot V1. K3 is Moonshot's 2.8T-parameter, native-vision flagship with a 1M-token context window; the official launch page lists the kimi-k3 model ID and cache-hit, cache-miss and output pricing. K2.7 Code remains the coding-focused agentic model with 256K context, a default 32K maximum output, native text, image and video input, ToolCalls, JSON Mode, Partial Mode, automatic context caching and mandatory thinking mode. The HighSpeed model uses the kimi-k2.7-code-highspeed ID and targets about 180 output tokens per second, reaching up to 260 tokens per second in short-context scenarios. The OpenAI-compatible API supports multimodal tool results, but K2.7 Code fixes its sampling parameters and requires reasoning_content to remain in context across multi-step tool calls. Chat Completions bills both input and output tokens; extracted document text is billed when passed to a model, while file storage and extraction interfaces are temporarily free.

Topic guide

Kimi models, API and agent workspace

A source-backed map of Kimi K3, K2.7 Code, the Kimi API, Kimi Code, Kimi Claw, WebBridge and productivity creation surfaces.

Editorial verdict

Best for

Developers evaluating Chinese long-context, coding and agentic models through an international API.

Avoid if

Avoid assuming consumer Kimi behavior or limits match API behavior.

Why it matters

Kimi's developer path is separated through K2.7 Code, K2.6 and the English API platform, so it should be distinct from the consumer assistant and Kimi Code CLI.

Trust: 6/6 sources verified, recently checkedCoverage: 100/100

Pricing

Pay-as-you-go API pricing varies by Kimi K2 and Moonshot model

Payment

Pay-as-you-go API billing, Platform billing, Enterprise sales

Commercial use

Commercial use should follow the current product, API, model license and billing terms.

Privacy

Review prompt, file, media upload, retention and training-use terms before sensitive workloads.

Use-case fit

Coding-agent API evaluation

Strong

Use K2.7 Code for long-horizon coding agents, tool calls and repository-scale workflows.

Long-context API evaluation

Strong

Use K2.7 Code, K2.6 or Moonshot V1 for 256K long-context prompts, file-like workloads and complex reasoning checks.

Multimodal agent API

Strong

Use text, base64 images, uploaded media and image or video tool results in agentic tasks; direct image URLs are not currently supported.

Global user checklist

RegistrationConfirmedKimi API platform provides English account and docs surfaces.
English UIConfirmedAPI docs, model pages and pricing pages are English-facing.
API and docsConfirmedDocs include OpenAI-compatible Chat Completions, model IDs, multimodal tool results, fixed parameter values and multi-step reasoning-content requirements.
International paymentPartialChat Completions bills input and output tokens, including extracted document text sent to a model. The June 11-July 2 rebate has ended; current file-storage, extraction and top-up terms must be checked in the account before purchase.

Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.

Pros

  • - K2.7 Code supports 256K context, multimodal input and coding-focused agent workflows
  • - OpenAI-compatible API path is documented
  • - Automatic context caching, ToolCalls, JSON Mode and Partial Mode are documented for K2.7 Code
  • - HighSpeed targets about 180 output tokens per second and up to 260 tokens per second for short contexts
  • - Multimodal tool results can return image or video content to the model
  • - File storage and file-content extraction interfaces are temporarily free
  • - The June 11-July 2 launch rebate is retained only as historical pricing context and is no longer active
  • - Pricing and model lists are English-facing

Cons

  • - Model generations and preview status can change quickly
  • - Consumer Kimi and API platform limits are separate
  • - HighSpeed capacity is currently limited and output speed may fluctuate
  • - Thinking, sampling and tool-choice parameters are constrained; unsupported values return errors
  • - Multi-step tool calls fail if reasoning_content from the assistant turn is omitted
  • - Extracted document content is billed as input once it is passed to a model
  • - Free file storage and extraction are explicitly temporary and may change
  • - Promotion participation is limited to once per Organization ID, vouchers expire after 90 days and top-ups are non-refundable

Decision paths

qwen

deepseek

zhipu-glm

Sources

Kimi K2.7 Code official resource

Official · EN · verified 2026-08-04

Confirms K2.7 Code positioning, benchmarks, architecture, Kimi Code access and API pricing.

Kimi K2.7 Code API pricing

Pricing · EN · verified 2026-06-17

Documents K2.7 Code and HighSpeed pricing page, model description, caching, ToolCalls, JSON Mode and Partial Mode.

Kimi K2.7 Code quickstart

Documentation · EN · verified 2026-06-21

Documents model IDs, HighSpeed throughput, context and output limits, OpenAI-compatible setup, multimodal tool results, media limits, fixed parameters and tool-call constraints.

Kimi model inference pricing

Pricing · EN · verified 2026-06-21

Explains token units, input and output billing, document-extraction billing, temporarily free file interfaces and the Token Calculation API.

Kimi K2.7 Code launch promotion

Pricing · EN · verified 2026-06-21

Confirms campaign dates, qualifying top-up tiers, voucher percentages, one-participation rule, issuance timing, $4,000 cap, 90-day validity and non-refundable top-ups.

Kimi model list

Documentation · EN · verified 2026-05-17

Lists K2.6, K2.5, K2 and Moonshot V1 model families.

Last checked: 2026-08-04

Reviews

No approved reviews yet.

Availability snapshot

Availability
Globally available
English UI
Full English UI
API
Public API
Rating
4.4 (0)

Latest updates

Latest changes
Release · 2026-07-17

Moonshot launches Kimi K3

Moonshot AI launched Kimi K3 as a hosted 2.8T-parameter, native-vision MoE model with a 1M-token context window. It became available in Kimi, Kimi Work, Kimi Code and the Kimi API as kimi-k3 at $0.30/M cache-hit input tokens, $3/M cache-miss input tokens and $15/M output tokens. At launch, Moonshot scheduled the full-weight release for July 27; that release is now tracked separately. Published limitations include sensitivity to dropped thinking history and possible over-proactiveness on ambiguous tasks.

Pricing · 2026-06-21

Kimi K2.7 Code launch top-up promotion recorded

Kimi API is running a K2.7 Code launch top-up rebate from June 11, 2026 at 09:00 PDT through July 2 at 08:59:59 PDT. A single top-up of $100-$299 receives a 20% voucher, $300-$999 receives 25%, and $1,000 or more receives 30%. Each Organization ID can participate once; the voucher is issued within one business day, capped at $4,000, valid for 90 days and usable across Kimi platform purchases. Top-up funds are non-refundable.

Pricing · 2026-06-21

Kimi API chat billing rules refreshed

Kimi API's model-pricing overview confirms that Chat Completions bills both input and output tokens. Document content is also billed as input when extracted text is sent to a model, while file storage and file-content extraction interfaces are temporarily free. Exact usage can be checked through the Token Calculation API; model-specific rates remain on the detailed K2.7 Code, K2.6 and Moonshot V1 pricing pages.

API · 2026-06-21

Kimi K2.7 Code API contract documented

Kimi's K2.7 Code quickstart documents the kimi-k2.7-code and kimi-k2.7-code-highspeed model IDs, a 256K context window and a default 32K maximum output. HighSpeed targets about 180 tokens per second and up to 260 tokens per second for short contexts, though capacity is currently limited. Thinking cannot be disabled; temperature, top_p, n and penalty values are fixed, tool_choice only accepts auto or none, and multi-step tool calls must preserve reasoning_content. The OpenAI-compatible API also supports image and video content in multimodal tool results.

Submit a review