LLM Reference

Kimi K3

Released
2026-07-14
Last refreshed
2026-07-16
Status
Researched 1d ago
Commercial use: unknownMultimodalRAGAgentsLong contextVisionJSON / Tool useHighlight

Kimi K3 is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 1.05m context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Kimi
Released
2026-07-14
Context
1.05m
Max output
1,048,576
Parameters
2.8T total; 16 of 896 experts active
Architecture
Mixture of Experts
Specialization
general
License
Unknown / UnverifiedCommercial use: unknown
Weights
Not released
Code
Unknown
Created by

Lossless long-context AI innovation

Beijing, China
Founded 2023
Website
Pricing
Output / 1M
$15.00
Input / 1M
$3.00

Cheapest of 1 route · Moonshot AI Kimi · cache read $0.300

About

Kimi K3 is Moonshot AI's 2.8-trillion-parameter flagship multimodal model for long-horizon coding, knowledge work, deep reasoning, and agentic workflows. It uses Kimi Delta Attention, Attention Residuals, and a sparse MoE design (16 of 896 experts active), supports a 1,048,576-token context window, text/image/video input, always-on reasoning, ToolCalls, strict JSON Schema structured output, automatic context caching, and partial mode through Moonshot's OpenAI-compatible API.

Kimi K3 is a model in the Kimi family. The structured metadata tracks a 1.05m-token context window, multimodal input, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through Moonshot AI Kimi, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include Program Bench 77.8, Terminal-Bench 2.1 88.3, and Google-Proof Q&A 93.5.

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 API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Moonshot AI Kimi$3.00$15.00read $0.300
Serverless

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsPrompt Caching

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(13)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Program Bench77.8KimiCode harness; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
Terminal-Bench 2.188.3Terminal-Bench 2.1; KimiCode harness; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
Google-Proof Q&A93.5GPQA-Diamond; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
Humanity's Last Exam43.5HLE-Full without tools; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
Humanity's Last Exam — With Tools56.0HLE-Full with tools; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
BrowseComp91.2BrowseComp; 300K-token context compaction; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
DeepSearchQA95.0DeepSearchQA F1; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
Toolathlon73.2Toolathlon-Verified; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
MCP-Atlas84.2500-task public subset; 100-turn limit; Gemini 3.1 Pro judge; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
AutomationBench30.8600-task public subset; official GitHub setup; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
WorldVQA51.0WorldVQA ForceAnswer; max reasoning effort; five-run meanhttps://www.kimi.com/blog/kimi-k3
MMMU Pro81.6MMMU-Pro; official protocol; three-run mean; max reasoning efforthttps://www.kimi.com/blog/kimi-k3
CharXiv84.8CharXiv RQ; three-run mean; max reasoning efforthttps://www.kimi.com/blog/kimi-k3

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Kimi K3?

Kimi K3 has a context window of 1.05m tokens.

What is the max output of Kimi K3?

Kimi K3 can generate up to 1,048,576 output tokens.

How much does Kimi K3 cost?

Kimi K3 is available at $3.00/1M input tokens through Moonshot AI Kimi.

When was Kimi K3 released?

Kimi K3 was released on 2026-07-14.

Which providers offer Kimi K3?

Kimi K3 is available from 1 provider: Moonshot AI Kimi.

What benchmarks has Kimi K3 been tested on?

Kimi K3 has been evaluated on 13 benchmarks, including Program Bench, Terminal-Bench 2.1, Google-Proof Q&A, Humanity's Last Exam, Humanity's Last Exam — With Tools.