What is the context window of Kimi K2.5?

Kimi K2.5 has a context window of 256k tokens.

How much does Kimi K2.5 cost?

Kimi K2.5 pricing ranges from $0.44/1M to $0.99/1M input tokens depending on the provider.

When was Kimi K2.5 released?

Kimi K2.5 was released on 2026-03-15.

What benchmarks has Kimi K2.5 been tested on?

Kimi K2.5 has been evaluated on 6 benchmarks, including Google-Proof Q&A, MMLU PRO, BFCL, τ-bench, MultiChallenge.

Kimi K2.5

Name: Kimi K2.5
Author: Moonshot AI

Released

2026-03-15

Last refreshed

2026-06-04

Status

Researched 1d ago

ProprietaryCommercial use with conditionsMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Kimi K2.5 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

Teams evaluating coding, rag, and agents
Workloads that can use a 256k context window
Buyers comparing 4 tracked provider routes

Do not use it for

Workloads where another current model has stronger sourced task evidence

Specifications

Family: Kimi
Released: 2026-03-15
Context: 256k
Parameters: 1T (MoE, 384 experts)
Architecture: Mixture of Experts
Specialization: code
Openness: Proprietary
License: ProprietaryCommercial use with conditions
Training: finetuned

Created by

Moonshot AI

Lossless long-context AI innovation

Beijing, China

Founded 2023

Website

Pricing

Output / 1M

$2.00

Input / 1M

$0.440

Cheapest of 11 routes · OpenRouter

Providers(11)

Cloudflare Workers AI Fireworks AI OpenRouter Together AI Fireworks AI NVIDIA NIM AWS Bedrock Replicate API Microsoft Foundry Vercel AI Gateway Novita AI

View 11 provider routes

About

Kimi K2.5 is Moonshot AI's Kimi model focused on code generation and software engineering. It offers a 256K-token context window and scores 87.9 on GPQA.

Kimi K2.5 is a proprietary model in the Kimi family. The structured metadata tracks a 256k-token context window, multimodal input, function calling, and structured outputs. This page tracks provider routes through Cloudflare Workers AI, Fireworks AI, OpenRouter, and 8 more, with the cheapest tracked route listed at $0.44 input and $2 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 87.9, MMLU PRO 87.1, and BFCL 47.1.

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

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ B

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 11

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
OpenRouter	$0.440	$2.00	Serverless
Together AI	$0.500	$2.80	Serverless
AWS Bedrock	$0.600	$3.00	Serverless
Fireworks AI	$0.600	$3.00	Serverless

Capabilities

VisionMultimodalFunction CallingStructured Outputs

Benchmark peer barsfor Agents

τ-benchRank 12 of 16

Claude Mythos Preview

89.2

87.5

84.8

82.1

74.2

MultiChallengeRank 3 of 9

Gemini 3.1 Pro Preview

71.4

GPT-5.4

69.2

Kimi K2.5current

61.4

Gemini 3.1 Flash Lite Preview

60.6

Claude Opus 4.7

58.6

Benchmark scores(6)

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.

Benchmark	Score	Version	Source
Google-Proof Q&A	87.9	diamond	https://artificialanalysis.ai/leaderboards/models
MMLU PRO	87.1	—	https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
BFCL	47.1	v4	https://gorilla.cs.berkeley.edu/leaderboard.html
τ-bench	74.2	τ-bench	https://taubench.com/
MultiChallenge	61.4	MultiChallenge	https://labs.scale.com/leaderboard/multichallenge
SWE-rebench	58.5	pass@1 (best of 5 runs)	https://swe-rebench.com/leaderboard