ModelBench
Moonshot AI logo
Models/Moonshot AI

Kimi K2 Thinking

Thinking Kimi model for slower research passes, planning, and hard technical questions

Source-linked kimi-thinking Open weights Released 2025-11-06
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.6/1M tokens
Output price$2.5/1M tokens
Context window262.144K
Max output262.144K
Overview

Capabilities and specifications

× Reasoning No
✓ Tool calling Yes
✓ Structured output Yes
× Attachments No
× Vision input No
✓ Open weights Yes
Model family
kimi-thinking
Knowledge cutoff
2024-08
License
Not documented
Release date
2025-11-06
Model ID
moonshotai/kimi-k2-thinking
Inference availability

Provider pricing and availability

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

Report a price
Providers offering Kimi K2 Thinking
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Qiniu moonshotai/kimi-k2-thinking 256K Not listed Not listed - Tools Docs
Kimi For Coding kimi-k2-thinking 262.144K Not listed Not listed - ReasoningToolsJSON Docs
NanoGPT moonshotai/kimi-k2-thinking 256K $0.3 $1.2 - ToolsJSON Docs
OpenCode Zen kimi-k2-thinking 262.144K $0.4 $2.5 $0.4 ReasoningTools Docs
Vercel AI Gateway moonshotai/kimi-k2-thinking 216.144K $0.47 $2 $0.141 ReasoningTools Docs
Kilo Gateway moonshotai/kimi-k2-thinking 131.072K $0.47 $2 $0.2 ReasoningTools Docs
Helicone kimi-k2-thinking 256K $0.48 $2 - Tools Docs
IO.NET moonshotai/Kimi-K2-Thinking 32.768K $0.55 $2.25 $0.275 ReasoningTools Docs
NovitaAI moonshotai/kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningToolsJSON Docs
Moonshot AI kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningTools Docs
ZenMux moonshotai/kimi-k2-thinking 262K $0.6 $2.5 $0.15 ReasoningTools Docs
Merge Gateway moonshotai/kimi-k2-thinking 262.144K $0.6 $2.5 - ReasoningTools Docs
LLM Gateway kimi-k2-thinking 262.144K $0.6 $2.5 $0.06 ReasoningTools Docs
Moonshot AI (China) kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningTools Docs
Azure kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningTools Docs
Meganova moonshotai/Kimi-K2-Thinking 262.144K $0.6 $2.6 - ReasoningTools Docs
Amazon Bedrock moonshot.kimi-k2-thinking 262.143K $0.6 $2.5 - ReasoningToolsJSON Docs
OpenRouter moonshotai/kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningToolsJSON Docs
Azure Cognitive Services kimi-k2-thinking 262.144K $0.6 $2.5 $0.15 ReasoningTools Docs
Vertex moonshotai/kimi-k2-thinking-maas 262.144K $0.6 $2.5 - 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 Thinking
1.8
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 Thinking
21.0
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 Thinking
1138.0
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 Thinking
17.3
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 Thinking
71.3
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Max Output Tokens100352 → 262144
Max Output Tokens262144 → 100352
Max Output Tokens100352 → 262144
Max Output Tokens262144 → 100352
Max Output Tokens100352 → 262144
Max Output Tokens262144 → 100352
Max Output Tokens100352 → 262144
Max Output Tokens262144 → 100352
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-thinking
curl
curl "https://www.modelbench.lol/api/v1/models/moonshotai/kimi-k2-thinking"