Kimi K2 API Benchmarks, Pricing & Provider Data
Compare Kimi K2 with another model
Choose a model to open its comparison page.
Kimi K2 benchmark, API pricing, and provider data cover 354 API providers, with prices starting at $0.010/request. Kimi K2 free API options are available from 1 provider. The page also shows measured API speed and first-token latency.
Moonshot Kimi K2 is a trillion-parameter MoE model from Moonshot AI, built for long-context chat, agentic tool use, and high-quality Chinese-English bilingual generation.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Math53.7Estimated3/4 Measured dimensions
#2Reasoning48.6RatedGlobal rank #473/4 Measured dimensions
#3Coding48.3Provisional1/4 Measured dimensions
#4Agents45.3Provisional1/4 Measured dimensions
#5Knowledge44.5Provisional1/4 Measured dimensions
#6Instruction following43.8Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Aug 31, 2026Overall
undefined metric} other undefined metrics}}
Overall score50.0#72 / 100
Overall
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.570/M#91 / 180Output price$2.30/M#82 / 180
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Score45.380% interval29.3–61.31/4 Measured dimensionsΤ²-bench results61.1#62 / 82
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score48.380% interval34.3–62.21/4 Measured dimensionsLiveCodeBench55.6%#50 / 115SciCode34.5%#132 / 205
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score48.6#4780% interval39.9–57.23/4 Measured dimensionsMMLU-Pro82.4%#47 / 129GPQA76.6%#111 / 212
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score44.580% interval28.5–60.51/4 Measured dimensionsArtificial Analysis Intelligence Index19.6#85 / 111AA-GPQA Diamond76.6#77 / 108
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score53.780% interval44.4–62.93/4 Measured dimensionsAIME69.3%#21 / 68MATH-50097.1%#12 / 73
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1061.0#66 / 75
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score43.880% interval27.8–59.81/4 Measured dimensionsAA-IFBench41.5#65 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
OpenRouter endpoints
1 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Novita novita/fp8 | $0.570/M | $2.30/M | 100.0% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Kimi K2 API pricing across 353 providers. Prices range from $0.010/request to $75.00/M. 素墨API offers the lowest rate at $0.010/request. 1 provider offers free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | kimi-k2-0711-preview | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2 | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2-250905 | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2-0711-preview | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2-250905 | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2 | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2-0905 | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2-0711-preview | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2-250905 | default | -4%$0.548/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2 | default | $10.27/M | $10.27/M | — | — | — | |
L1 100% | kimi-k2-0711-preview | default | $2.00/M Cache read$0.200/M | -13%$2.00/M | — | — | — | |
L1 100% | kimi-k2-0905-preview | default | $4.00/M Cache read$0.400/M | $16.00/M | — | — | — | |
兔子API Free | L1 100% | Kimi-K2-0905 | 原价分组 | Free | Free | — | — | — |
L1 100% | kimi-k2-0711-preview | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2-250905 | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2 | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 100% | kimi-k2-0905 | default | -52%$0.274/M | -52%$1.10/M | — | — | — | |
L1 99% | kimi-k2 | other | -56%$0.250/M Cache read$0.150/M | -55%$1.04/M | — | — | — | |
L1 100% | kimi-k2-0905-preview | default | -4%$0.548/M Cache read$0.137/M | -5%$2.19/M | — | — | — | |
L1 100% | kimi-k2-0711-preview | default | -4%$0.548/M Cache read$0.137/M | -5%$2.19/M | — | — | — |
Alternatives & Similar Models
DeepSeek V3.2
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
GLM-4.7
glm-4-7
Zhipu GLM-4.7 is a flagship GLM release from Zhipu AI with advanced Chinese-English reasoning, coding, and agent features.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
Qwen3
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
Frequently Asked Questions
- What benchmark data does Kimi K2 include?
- LMSpeed shows Kimi K2 benchmark context, API price, output speed, first-token latency, and provider data across 354 providers when those signals are available.
- What is the Kimi K2 API price?
- Kimi K2 has pricing from 354 providers, ranging from $0.010/request to $75.00/M. 素墨API has the lowest listed price.
- What does the Kimi K2 API pricing table include?
- The Kimi K2 API pricing table compares 354 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Kimi K2 API pricing?
- 素墨API currently has the lowest listed Kimi K2 price at $0.010/request across 354 providers.
- Can I compare Kimi K2 API price and speed together?
- Yes. LMSpeed shows Kimi K2 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Kimi K2 API free?
- Yes, Kimi K2 free API options are available through 1 providerundefined other undefined} on LMSpeed, including 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Kimi K2 free API access?
- LMSpeed currently lists 1 free API providerundefined other undefined} for Kimi K2: 兔子API. Check each provider row before using it because free tier limits can change.