ModelBench
Moonshot AI logo
Models/Moonshot AI

Kimi K2.6

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Source-linked kimi-k2 Open weights Released 2026-04-21
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.95/1M tokens
Output price$4/1M 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
2026-04-21
Model ID
moonshotai/kimi-k2.6
Inference availability

Provider pricing and availability

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

Report a price
Providers offering Kimi K2.6
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Alibaba Token Plan (China) kimi-k2.6 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Kenari kimi-k2-6 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Nvidia moonshotai/kimi-k2.6 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Alibaba Token Plan kimi-k2.6 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Privatemode AI kimi-k2.6 262.144K Not listed Not listed - ReasoningToolsJSON Docs
LLM Gateway kimi-k2.6 262.144K $0.22 $1.137 $0.048 ReasoningToolsJSON Docs
routing.run kimi-k2.6 200K $0.275 $1.1 - ReasoningToolsJSON Docs
Vultr moonshotai/Kimi-K2.6 262.144K $0.3 $1.2 - ReasoningToolsJSON Docs
CrofAI kimi-k2.6 262.144K $0.5 $1.99 $0.05 ReasoningToolsJSON Docs
NanoGPT moonshotai/kimi-k2.6 256K $0.53 $2.73 - Tools Docs
Weights & Biases moonshotai/Kimi-K2.6 262.144K $0.65 $3.41 $0.15 ReasoningToolsJSON Docs
Inceptron moonshotai/Kimi-K2.6 262.144K $0.66 $3.5 $0.2 ReasoningToolsJSON Docs
Neuralwatt moonshotai/Kimi-K2.6 262.128K $0.69 $3.22 $0.172 ReasoningTools Docs
Lilac moonshotai/kimi-k2.6 262.144K $0.7 $3.5 $0.2 ReasoningToolsJSON Docs
Venice AI kimi-k2-6 256K $0.75 $3.5 $0.16 ReasoningToolsJSON Docs
Deep Infra moonshotai/Kimi-K2.6 262.144K $0.75 $3.5 $0.15 ReasoningToolsJSON Docs
Kilo Gateway moonshotai/kimi-k2.6 262.144K $0.75 $3.5 $0.375 ReasoningToolsJSON Docs
FastRouter moonshotai/kimi-k2.6 262.144K $0.75 $3.5 - ReasoningToolsJSON Docs
NovitaAI moonshotai/kimi-k2.6 262.144K $0.8 $3.4 $0.16 ReasoningToolsJSON Docs
GreenPT kimi-k2.6 262.144K $0.828 $4.389 - ReasoningToolsJSON Docs
Berget.AI moonshotai/Kimi-K2.6 262.144K $0.83 $3.85 $0.16 ReasoningToolsJSON Docs
ai& moonshotai/kimi-k2.6 262.144K $0.85 $3.5 - ReasoningToolsJSON Docs
GMI Cloud moonshotai/Kimi-K2.6 65.536K $0.855 $3.6 $0.144 ReasoningToolsJSON Docs
EmpirioLabs AI kimi-k2-6 256K $0.894 $3.713 $0.179 ReasoningToolsJSON Docs
EBCloud Kimi-K2.6 262.144K $0.929 $3.857 - ReasoningToolsJSON Docs
Vercel AI Gateway moonshotai/kimi-k2.6 262K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Moonshot AI kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Auriko kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Cloudflare Workers AI @cf/moonshotai/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
OpenCode Go kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningTools Docs
DigitalOcean kimi-k2.6 262.144K $0.95 $4 - ReasoningToolsJSON Docs
ZenMux moonshotai/kimi-k2.6 262.14K $0.95 $4 $0.16 ReasoningTools Docs
Merge Gateway moonshotai/kimi-k2.6 262.144K $0.95 $4 - ReasoningToolsJSON Docs
OrcaRouter kimi/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Pioneer moonshotai/Kimi-K2.6 262.144K $0.95 $4 $0.34 ReasoningToolsJSON Docs
Abacus moonshotai/Kimi-K2.6 262.144K $0.95 $4 $0.19 ReasoningToolsJSON Docs
Cloudflare AI Gateway workers-ai/@cf/moonshotai/kimi-k2.6 256K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Moonshot AI (China) kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Azure kimi-k2.6 262.144K $0.95 $4 - ReasoningToolsJSON Docs
OpenCode Zen kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningTools Docs
OpenRouter moonshotai/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Azure Cognitive Services kimi-k2.6 262.144K $0.95 $4 - ReasoningToolsJSON Docs
Baseten moonshotai/Kimi-K2.6 262K $0.95 $4 $0.16 ReasoningToolsJSON Docs
AIHubMix kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Ambient moonshotai/kimi-k2.6 262.144K $0.95 $4 $0.2 ReasoningToolsJSON Docs
Clarifai moonshotai/chat-completion/models/Kimi-K2_6 262.144K $0.95 $4 - ReasoningToolsJSON Docs
ClinePass cline-pass/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Ofox moonshotai/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Merge Gateway moonshot/kimi-k2.6 262.144K $0.95 $4 $0.16 ReasoningToolsJSON Docs
Charm Hyper kimi-k2.6 262K $0.95 $4 - ReasoningToolsJSON Docs
CrossModel moonshot/kimi-k2.6 262K $1 $4.16 $0.18 ReasoningToolsJSON Docs
Wafer Kimi-K2.6 262.144K $1.14 $4.8 $0.19 ReasoningToolsJSON Docs
Together AI moonshotai/Kimi-K2.6 262.144K $1.2 $4.5 $0.2 ReasoningToolsJSON Docs
UnoRouter kimi-k2.6 262.144K $1.268 $5.337 - ReasoningToolsJSON Docs
evroc moonshotai/Kimi-K2.6 262.144K $1.438 $5.75 - ReasoningToolsJSON Docs
Tinfoil kimi-k2-6 256K $1.5 $5.25 - 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 K2.6
30.3
Artificial Analysis Coding Agent Index - Unversioned - average pass@1 - Claude CodeTop 6 reported models
Claude Opus 4.7
59.9
GLM-5.1
52.7
Claude Opus 4.6
51.3
Kimi K2.6
50.5
DeepSeek V4 Pro
50.1
Claude Sonnet 4.6
49.4
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 K2.6
61.8
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 K2.6
1332.0
Design Arena: agenticgamedev - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1296.0
Claude Fable 5
1296.0
Anthropic: Claude Opus 4.8 (batch)
1259.0
Anthropic: Claude Opus 4.8
1259.0
Anthropic: Claude Opus 4.7 (batch)
1254.0
Anthropic: Claude Opus 4.7
1254.0
Anthropic: Claude Sonnet 5 (batch)
1238.0
Kimi K2.6
1151.0
Design Arena: agentichtmlslides - Unversioned - eloTop 7 reported models
Anthropic: Claude Fable 5 (batch)
1254.0
Claude Fable 5
1254.0
Kimi K2.6
1248.0
Anthropic: Claude Opus 4.7 (batch)
1243.0
Anthropic: Claude Opus 4.7
1243.0
Anthropic: Claude Opus 4.8 (batch)
1227.0
Anthropic: Claude Opus 4.8
1227.0
Design Arena: agenticslides - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.7 (batch)
1334.0
Anthropic: Claude Opus 4.7
1334.0
Anthropic: Claude Opus 4.8 (batch)
1294.0
Anthropic: Claude Opus 4.8
1294.0
Z.ai: GLM 5.1
1245.0
Google: Gemini 3.5 Flash (batch)
1244.0
Gemini 3.5 Flash
1244.0
Kimi K2.6
1187.0
Design Arena: agenticslides(html) - Unversioned - eloTop 7 reported models
Anthropic: Claude Fable 5 (batch)
1252.0
Kimi K2.6
1252.0
Claude Fable 5
1252.0
Anthropic: Claude Opus 4.7 (batch)
1242.0
Anthropic: Claude Opus 4.7
1242.0
Anthropic: Claude Opus 4.8 (batch)
1230.0
Anthropic: Claude Opus 4.8
1230.0
Design Arena: agenticslides(python-pptx) - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.7 (batch)
1331.0
Anthropic: Claude Opus 4.7
1331.0
Anthropic: Claude Opus 4.8 (batch)
1310.0
Anthropic: Claude Opus 4.8
1310.0
Google: Gemini 3.5 Flash (batch)
1242.0
Gemini 3.5 Flash
1242.0
Z.ai: GLM 5.1
1240.0
Kimi K2.6
1186.0
Design Arena: androidnative - Unversioned - eloTop 7 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
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 K2.6
1189.0
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 K2.6
1308.0
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 K2.6
1288.0
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 K2.6
1200.0
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 K2.6
1304.0
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 K2.6
1166.0
Design Arena: htmlslides - Unversioned - eloTop 8 reported models
Anthropic: Claude Fable 5 (batch)
1260.0
Claude Fable 5
1260.0
Anthropic: Claude Opus 4.7 (batch)
1244.0
Anthropic: Claude Opus 4.7
1244.0
Anthropic: Claude Opus 4.8 (batch)
1239.0
Anthropic: Claude Opus 4.8
1239.0
Anthropic: Claude Sonnet 5 (batch)
1234.0
Kimi K2.6
1226.0
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 K2.6
1243.0
Design Arena: pptxslides - Unversioned - eloTop 8 reported models
Anthropic: Claude Opus 4.7 (batch)
1333.0
Anthropic: Claude Opus 4.7
1333.0
Anthropic: Claude Opus 4.8 (batch)
1306.0
Anthropic: Claude Opus 4.8
1306.0
Google: Gemini 3.5 Flash (batch)
1244.0
Gemini 3.5 Flash
1244.0
Z.ai: GLM 5.1
1241.0
Kimi K2.6
1181.0
Design Arena: python-pptxslides - Unversioned - eloTop 8 reported models
Kimi K3
1380.0
Anthropic: Claude Opus 4.7 (batch)
1336.0
Anthropic: Claude Opus 4.7
1336.0
Anthropic: Claude Fable 5 (batch)
1301.0
Claude Fable 5
1301.0
Anthropic: Claude Opus 4.8 (batch)
1298.0
Anthropic: Claude Opus 4.8
1298.0
Kimi K2.6
1180.0
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 K2.6
1228.0
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 K2.6
1300.0
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 K2.6
1268.0
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 K2.6
1301.0
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 K2.6
44.2
SWE-Atlas Codebase QnA - Unversioned - pass@1 - Claude CodeTop 6 reported models
GLM-5.1
73.2
Claude Opus 4.6
71.9
Claude Opus 4.7
71.7
Claude Sonnet 4.6
70.3
DeepSeek V4 Pro
67.8
Kimi K2.6
59.8
SWE-Bench Pro - Unversioned - pass@1 - Claude CodeTop 6 reported models
Claude Opus 4.7
36.4
Kimi K2.6
27.3
GLM-5.1
19.8
DeepSeek V4 Pro
18.0
Claude Sonnet 4.6
14.9
Claude Opus 4.6
11.8
SWE-Bench Verified - Unversioned - resolvedTop 7 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
Terminal-Bench - 2.1 - pass@1 - Claude CodeTop 6 reported models
Claude Opus 4.7
71.4
Claude Opus 4.6
70.2
GLM-5.1
65.1
DeepSeek V4 Pro
64.7
Kimi K2.6
64.3
Claude Sonnet 4.6
63.1
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Price Completion2.7199999999999998 → 4.0
Price Prompt0.646 → 0.95
Price Completion4.0 → 2.7199999999999998
Price Prompt0.95 → 0.646
Price Completion2.7199999999999998 → 4.0
Price Prompt0.646 → 0.95
Price Completion4.0 → 2.7199999999999998
Price Prompt0.95 → 0.646
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-k2.6
curl
curl "https://www.modelbench.lol/api/v1/models/moonshotai/kimi-k2.6"