ModelBench
Moonshot AI logo
Models/Moonshot AI

Kimi K2.5

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Source-linked kimi-k2 Open weights Released 2026-01
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.6/1M tokens
Output price$3/1M tokens
Context window262.144K
Max output262.144K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Model family
kimi-k2
Knowledge cutoff
2025-01
License
Not documented
Release date
2026-01
Model ID
moonshotai/kimi-k2.5
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Kimi K2.5
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Qiniu moonshotai/kimi-k2.5 256K Not listed Not listed - Tools Docs
Alibaba Token Plan (China) kimi-k2.5 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Alibaba Coding Plan (China) kimi-k2.5 262.144K Not listed Not listed - ReasoningTools Docs
Alibaba Coding Plan kimi-k2.5 262.144K Not listed Not listed - ReasoningTools Docs
Alibaba Token Plan kimi-k2.5 262.144K Not listed Not listed - ReasoningToolsJSON Docs
NanoGPT moonshotai/kimi-k2.5 256K $0.3 $1.9 - Tools Docs
CrofAI kimi-k2.5 262.144K $0.35 $1.7 $0.07 ReasoningToolsJSON Docs
LLM Gateway kimi-k2.5 262.144K $0.405 $1.98 $0.225 ReasoningToolsJSON Docs
Deep Infra moonshotai/Kimi-K2.5 262.144K $0.45 $2.25 $0.07 ReasoningToolsJSON Docs
Kilo Gateway moonshotai/kimi-k2.5 262.144K $0.45 $2.2 - ReasoningTools Docs
Meganova moonshotai/Kimi-K2.5 262.144K $0.45 $2.8 - ReasoningTools Docs
Auriko kimi-k2.5 262.144K $0.5 $2.8 - ReasoningToolsJSON Docs
DigitalOcean kimi-k2.5 262.144K $0.5 $2.7 - ReasoningToolsJSON Docs
Together AI moonshotai/Kimi-K2.5 262.144K $0.5 $2.8 - ReasoningTools Docs
Neuralwatt moonshotai/Kimi-K2.5 262.128K $0.52 $2.59 $0.13 ReasoningTools Docs
Charm Hyper kimi-k2.5 262.144K $0.534 $2.82 - ToolsJSON Docs
Venice AI kimi-k2-5 256K $0.56 $3.5 $0.22 ReasoningToolsJSON Docs
OpenRouter moonshotai/kimi-k2.5 262.144K $0.57 $2.85 $0.095 ReasoningToolsJSON Docs
ZenMux moonshotai/kimi-k2.5 262K $0.58 $3.02 $0.1 ReasoningTools Docs
Vercel AI Gateway moonshotai/kimi-k2.5 262.114K $0.6 $3 $0.1 ReasoningToolsJSON Docs
NovitaAI moonshotai/kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Moonshot AI kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
OpenCode Go kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningTools Docs
Merge Gateway moonshotai/kimi-k2.5 262.144K $0.6 $3 - ReasoningToolsJSON Docs
OrcaRouter kimi/kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Abacus kimi-k2.5 262.144K $0.6 $3 - ReasoningToolsJSON Docs
Cloudflare AI Gateway workers-ai/@cf/moonshotai/kimi-k2.5 256K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Moonshot AI (China) kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
DaoXE kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Azure kimi-k2.5 262.144K $0.6 $3 - ReasoningToolsJSON Docs
OpenCode Zen kimi-k2.5 262.144K $0.6 $3 $0.08 ReasoningTools Docs
HPC-AI moonshotai/kimi-k2.5 256K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Weights & Biases moonshotai/Kimi-K2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Jiekou.AI moonshotai/kimi-k2.5 262.144K $0.6 $3 - ReasoningToolsJSON Docs
Azure Cognitive Services kimi-k2.5 262.144K $0.6 $3 - ReasoningToolsJSON Docs
Baseten moonshotai/Kimi-K2.5 262K $0.6 $3 $0.12 ReasoningToolsJSON Docs
AIHubMix kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
Merge Gateway moonshot/kimi-k2.5 262.144K $0.6 $3 $0.1 ReasoningToolsJSON Docs
CrossModel moonshot/kimi-k2.5 262K $0.62 $3.3 $0.11 ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Agentic Index - Unversioned - indexTop 8 reported models
Claude Opus 5
55.3
GPT-5.6 Sol
54.0
Anthropic: Claude Fable 5 (batch)
52.8
Claude Fable 5
52.8
Kimi K3
50.1
GPT-5.6 Terra
47.4
Anthropic: Claude Opus 4.8 (batch)
47.2
Kimi K2.5
21.7
Coding Index - Unversioned - indexTop 8 reported models
Claude Opus 5
78.0
GPT-5.6 Sol
77.4
GPT-5.6 Terra
76.7
Anthropic: Claude Fable 5 (batch)
76.5
Claude Fable 5
76.5
Kimi K3
76.2
OpenAI: GPT-5.5 (batch)
74.9
Kimi K2.5
46.8
Design Arena: 3d - Unversioned - eloTop 8 reported models
Kimi K3
1456.0
Claude Opus 5
1384.0
Anthropic: Claude Fable 5 (batch)
1373.0
Claude Fable 5
1373.0
Z.ai: GLM 5.2
1366.0
Z.ai: GLM 5.1
1336.0
Anthropic: Claude Opus 4.6 (batch)
1332.0
Kimi K2.5
1262.0
Design Arena: androidnative - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.8 (batch)
1337.0
Anthropic: Claude Opus 4.8
1337.0
Anthropic: Claude Fable 5 (batch)
1306.0
Claude Fable 5
1306.0
xAI: Grok 4.5
1280.0
Kimi K2.6
1278.0
Z.ai: GLM 5V Turbo
1267.0
Kimi K2.5
1105.0
Design Arena: asciiart - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1364.0
Claude Fable 5
1364.0
Anthropic: Claude Opus 4.7 (batch)
1324.0
Anthropic: Claude Opus 4.7
1324.0
Muse Spark 1.1
1322.0
Google: Gemini 3.1 Pro Preview (batch)
1309.0
Gemini 3.1 Pro Preview
1309.0
Kimi K2.5
1204.0
Design Arena: codecategories - Unversioned - eloTop 8 reported models
Kimi K3
1418.0
Claude Opus 5
1358.0
Z.ai: GLM 5.2
1346.0
Anthropic: Claude Fable 5 (batch)
1340.0
Claude Fable 5
1340.0
Anthropic: Claude Opus 4.6 (batch)
1324.0
Anthropic: Claude Opus 4.6
1324.0
Kimi K2.5
1268.0
Design Arena: dataviz - Unversioned - eloTop 8 reported models
Kimi K3
1382.0
Claude Opus 5
1378.0
Z.ai: GLM 5.1
1366.0
Google: Gemini 3.6 Flash (batch)
1350.0
Gemini 3.6 Flash
1350.0
Anthropic: Claude Fable 5 (batch)
1349.0
Claude Fable 5
1349.0
Kimi K2.5
1251.0
Design Arena: fullstack - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.7 (batch)
1503.0
Anthropic: Claude Opus 4.7
1503.0
Anthropic: Claude Fable 5 (batch)
1293.0
Claude Fable 5
1293.0
Anthropic: Claude Opus 4.8 (batch)
1289.0
Anthropic: Claude Opus 4.8
1289.0
xAI: Grok 4.5
1282.0
Kimi K2.5
1155.0
Design Arena: gamedev - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1393.0
Claude Fable 5
1393.0
Z.ai: GLM 5.2
1358.0
Anthropic: Claude Sonnet 5 (batch)
1352.0
Claude Sonnet 5
1352.0
OpenAI: GPT-5.5 (batch)
1345.0
GPT-5.5
1345.0
Kimi K2.5
1262.0
Design Arena: godotgamedev - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1349.0
Claude Fable 5
1349.0
Anthropic: Claude Opus 4.7 (batch)
1270.0
Anthropic: Claude Opus 4.7
1270.0
xAI: Grok 4.5
1270.0
Anthropic: Claude Sonnet 5 (batch)
1269.0
Claude Sonnet 5
1269.0
Kimi K2.5
1219.0
Design Arena: mobileapps - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.6 (batch)
1275.0
Anthropic: Claude Opus 4.6
1275.0
Anthropic: Claude Opus 4.8 (batch)
1272.0
Anthropic: Claude Opus 4.8
1272.0
Anthropic: Claude Sonnet 4.6
1267.0
Anthropic: Claude Fable 5 (batch)
1265.0
Claude Fable 5
1265.0
Kimi K2.5
1176.0
Design Arena: svg - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1351.0
Claude Fable 5
1351.0
Google: Gemini 3.1 Pro Preview (batch)
1335.0
Gemini 3.1 Pro Preview
1335.0
Google: Gemini 3.5 Flash (batch)
1296.0
Gemini 3.5 Flash
1296.0
Anthropic: Claude Opus 4.6 (batch)
1276.0
Kimi K2.5
1194.0
Design Arena: uicomponent - Unversioned - eloTop 8 reported models
Kimi K3
1413.0
Claude Opus 5
1406.0
Anthropic: Claude Fable 5 (batch)
1350.0
Claude Fable 5
1350.0
Anthropic: Claude Opus 4.7 (batch)
1339.0
Anthropic: Claude Opus 4.7
1339.0
Z.ai: GLM 5.2
1334.0
Kimi K2.5
1272.0
Design Arena: webapps - Unversioned - eloTop 8 reported models
Kimi K3
1329.0
Anthropic: Claude Fable 5 (batch)
1305.0
Claude Fable 5
1305.0
Anthropic: Claude Sonnet 5 (batch)
1304.0
Claude Sonnet 5
1304.0
Anthropic: Claude Opus 4.7 (batch)
1303.0
Anthropic: Claude Opus 4.7
1303.0
Kimi K2.5
1177.0
Design Arena: website - Unversioned - eloTop 8 reported models
Kimi K3
1375.0
Claude Opus 5
1343.0
Z.ai: GLM 5.2
1340.0
Anthropic: Claude Fable 5 (batch)
1323.0
Claude Fable 5
1323.0
xAI: Grok 4.5
1323.0
Google: Gemini 3.6 Flash (batch)
1322.0
Kimi K2.5
1275.0
Intelligence Index - Unversioned - indexTop 8 reported models
Claude Opus 5
60.7
Anthropic: Claude Fable 5 (batch)
59.9
Claude Fable 5
59.9
GPT-5.6 Sol
58.9
Kimi K3
57.1
Anthropic: Claude Opus 4.8 (batch)
55.7
Anthropic: Claude Opus 4.8
55.7
Kimi K2.5
35.4
SWE-Atlas Codebase QnA - Unversioned - score - Mini-SWE-AgentTop 7 reported models
GPT-5.4
36.3
Claude Opus 4.6
30.0
GLM-5
20.5
Gemini 3.1 Pro Preview
13.5
Kimi K2.5
13.1
MiniMax-M2.5
10.3
Gemini 3 Flash Preview
8.2
SWE-Atlas Refactoring - Unversioned - score - Mini-SWE-AgentTop 4 reported models
GLM-5
24.2
Kimi K2.5
20.9
MiniMax-M2.5
19.5
Gemini 3 Flash Preview
10.0
SWE-Atlas Test Writing - Unversioned - score - Mini-SWE-AgentTop 7 reported models
GPT-5.4
40.0
Claude Opus 4.6
36.1
Gemini 3 Flash Preview
30.3
Gemini 3.1 Pro Preview
29.8
GLM-5
28.7
Kimi K2.5
25.8
MiniMax-M2.5
18.6
SWE-Bench Verified - Unversioned - resolvedTop 8 reported models
Claude Fable 5
95.0
Claude Opus 4.8
88.6
Claude Sonnet 5
85.2
DeepSeek V4 Pro
80.6
Qwen3.7 Max
80.4
Kimi K2.6
80.2
DeepSeek V4 Flash
79.0
Kimi K2.5
70.8
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Price Completion2.8499999999999996 → 3.0
Price Prompt0.5700000000000001 → 0.6
Price Completion3.0 → 2.8499999999999996
Price Prompt0.6 → 0.5700000000000001
Price Completion2.8499999999999996 → 3.0
Price Prompt0.5700000000000001 → 0.6
Price Completion3.0 → 2.8499999999999996
Price Prompt0.6 → 0.5700000000000001
Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/moonshotai/kimi-k2.5
curl
curl "https://www.modelbench.lol/api/v1/models/moonshotai/kimi-k2.5"