WritingmateWritingmate

AI model reference · 2026

Kimi K2.5

MoonshotAI: Kimi K2.5 logoMoonshot AIModel details, evidence, and API facts

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.

Text generation
Image input
Reasoning
Provider endpoint accepts tool parameters
Try Kimi K2.5Compare with another model
Context window
262,144 tokens
Maximum output
235,929 tokens
Base provider API input
$0.45 / 1M tokens
Base provider API rate
Published evidence
2 benchmarks, 0 Arena results

Overview

About Kimi K2.5

A concise catalog overview. Technical limits and published evaluation evidence are listed separately below.

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.

text
multimodal
reasoning

Published evaluations

Benchmark results

Only results mapped to this exact model and backed by a named source appear here. Different evaluation protocols are not treated as interchangeable.

Source-backed benchmark results for Kimi K2.5
BenchmarkScoreEvaluation detailsSource
OSWorld-VerifiedA verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state.63.3%Mean task rewardVersion: OSWorld-Verified v1 · Split: Up to 361 tasks, excluding eight Google Drive tasks where required · Harness: Official OSWorld unified environment · Attempts: One run · Tools: GUI interactionProtocol note: Only 100-step general-model rows are included in this normalized snapshot. Individual evaluated-task counts can differ when a task could not run.; Run date: 2026-01-30; Evaluated tasks: 361Methodology OSWorldBenchmark owner
SWE-Bench VerifiedA human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests.70.8%ResolvedVersion: SWE-Bench Verified 500 · Split: Verified, 500 tasks · Harness: mini-SWE-agent / version 2.0.0 · Attempts: One attempt · Reasoning effort: highProtocol note: Harness version: 2.0.0; Run date: 2026-02-17Methodology SWE-benchBenchmark owner

Human preference

Arena results

Arena scores come from blind human preference votes. They are reported separately from task benchmarks and are not used as substitutes for missing benchmark results.

No exact Arena match is available for this model. Similar names and provider variants are not merged automatically.

Technical reference

Specifications and API facts

Technical limits and reference provider prices come from the current catalog unless a reviewed external source is listed. Missing values stay marked as unavailable.

Model
Provider
Moonshot AI
Release date
Not available in reviewed sources
Catalog added
Jan 27, 2026
Context window
262,144 tokens
Maximum output
235,929 tokens
Knowledge cutoff
Not available in reviewed sources
License
Not available in reviewed sources
Capabilities and API
Input types
Text, Image
Output types
Text
Reasoning
Supported
Provider endpoint tool parameters
Accepts tool parameters
Base provider API input
$0.45 / 1M tokens
Base provider cached input
$0.07 / 1M tokens
Base provider API output
$2.25 / 1M tokens

These are reference provider API rates, not Writingmate checkout charges. Access in Writingmate follows the allowances of your Writingmate plan.

Provenance

Sources and update status

Source links are attached to the facts and evaluations they support. Catalog-only values are not presented as independently verified claims.

Evidence last updated Aug 9, 2026.

Catalog record updated Jan 27, 2026.

Catalog-added dates describe when a model entered the catalog, not necessarily its public release date.

Try Kimi K2.5 in Writingmate

Use this model, then compare its response with other AI models in the same workspace.

Get startedCompare models