openrouter

kimi-k2

completions

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Input:$0.09 / 1M tokens
Output:$0.09 / 1M tokens
Context:32768 tokens
text
text
Category Rankings
academia#16
finance#14
marketing#6
maths#16
writing#13

Access kimi-k2 through LangDB AI Gateway

Recommended

Integrate with moonshotai's kimi-k2 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Code Example
Configuration
Base URL
API Keys
Headers
Project ID in header
X-Run-Id
X-Thread-Id
Model Parameters
13 available
frequency_penalty
-202
logit_bias
logprobs
max_tokens
min_p
001
presence_penalty
-201.999
repetition_penalty
012
seed
stop
temperature
012
top_k
top_logprobs
top_p
011
Additional Configuration
Tools
Guards
User:
Id:
Name:
Tags:
Publicly Shared Threads1
  • openrouter
    Discussion about Data Extraction using Kimi K2
Popular Models10
  • deepseek
    DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
    Input:$0.25 / 1M tokens
    Output:$0.85 / 1M tokens
    Context:163840 tokens
    text
    text
  • deepseek
    DeepSeek-Chat is an advanced conversational AI model designed to provide intelligent
    Input:$0.14 / 1M tokens
    Output:$0.28 / 1M tokens
    Context:64K tokens
    tools
    text
    text
  • openai
    gpt-4.1
    openai
    GPT-4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.
    Input:$2 / 1M tokens
    Output:$8 / 1M tokens
    Context:1047576 tokens
    tools
    text
    image
    text
  • deepseek
    deepseek-r1
    deepseek
    DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!
    Input:$0.4 / 1M tokens
    Output:$2 / 1M tokens
    Context:163840 tokens
    text
    text
  • deepseek
    DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought. The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.
    Input:$0.01 / 1M tokens
    Output:$0.02 / 1M tokens
    Context:32K tokens
    text
    text
  • langdb
    Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence.
    Input:$0.1 / 1M tokens
    Output:$0.4 / 1M tokens
    Context:1048576 tokens
    tools
    text
    image
    text
  • deepseek
    May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.
    Input:$0.27 / 1M tokens
    Output:$0.27 / 1M tokens
    Context:163840 tokens
    text
    text
  • gemini
    Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems.
    Input:$1.25 / 1M tokens
    Output:$10 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text
  • openai
    GPT-4.1 nano is the fastest, most cost-effective GPT-4.1 model.
    Input:$0.1 / 1M tokens
    Output:$0.4 / 1M tokens
    Context:1047576 tokens
    tools
    text
    image
    text
  • aion-labs
    Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.
    Input:$0.2 / 1M tokens
    Output:$0.2 / 1M tokens
    Context:32768 tokens
    text
    text