Kimi K2

Name: Kimi K2
Author: Moonshot AI

Released

2025-07-11

Last refreshed

2026-06-15

Status

Researched 31d ago

DeprecatedOpen sourceCommercial use: permittedRAGAgentsLong contextClassificationJSON / Tool use

Kimi K2 is a legacy integration reference; evaluate Kimi K2.6 before starting new work.

Use it for

Teams maintaining an existing integration
Workloads that can use a 262k context window

Do not use it for

New production launches
Cost-sensitive launches that need sourced token pricing
Vision or document-understanding workloads

Specifications

Family: Kimi K2
Released: 2025-07-11
Context: 262k
Parameters: 1K
Openness: Open source
License: MITOSI-approvedCommercial use: permitted
Weights: Unknown
Code: Unknown

Created by

Moonshot AI

Lossless long-context AI innovation

Beijing, China

Founded 2023

Website

Pricing

No tracked provider token pricing is available yet.

Providers(3)

OpenRouter AWS Bedrock GCP Vertex AI

View 3 provider routes

Links

Website

This model is deprecated. Moonshot AI recommends switching to Kimi K2.6.

About

Original Kimi K2 model from Moonshot AI. Moonshot discontinued the Kimi K2 series API IDs on 2026-05-25; use kimi-k2-6 as the current successor.

Kimi K2 is an open-source model. The structured metadata tracks a 262k-token context window, function calling, and structured outputs. This page tracks provider routes through OpenRouter, AWS Bedrock, and GCP Vertex AI, with the cheapest tracked route listed at $0.5 input and $2 output per 1M tokens. No headline benchmark score is tracked for Kimi K2 yet.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 3

No tracked provider token pricing is available for this model yet.

Available via routers & gateways(14)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSGCP Vertex AI

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughGCP Vertex AI

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionGCP Vertex AI

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeGCP Vertex AI

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

SubscriptionGCP Vertex AI