Choose a model to open its comparison page.
Kimi K2 Thinking benchmark, API pricing, and provider data cover 58 API providers, with prices starting at $0.010/request. Kimi K2 Thinking free API options are available from 1 provider. The page also shows measured API speed and first-token latency.
Moonshot AI Kimi K2 Thinking is a reasoning model in the Kimi series, designed for complex reasoning, problem-solving, and analytical tasks.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 metrics
2 metrics
0 metrics · No data
2 metrics · Provisional
3 metrics · Estimated
0 metrics · No data
0 metrics · Provisional
0 metrics · No data
0 metrics · No data
0 metrics · No data
Third-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 |
|---|---|---|---|---|---|---|
Google google-vertex | $0.600/M | $2.50/M | 99.9% | — | — | 262.1K tokens / 262.1K tokens |
Novita novita/bf16 | $0.600/M | $2.50/M | 99.2% | — | — | 262.1K tokens / 100.4K tokens |
Compare Kimi K2 Thinking API pricing across 57 providers. Prices range from $0.010/request to $100.00/request. 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-thinking | default | -95%$0.027/M Cache read$0.027/M | -93%$0.171/M | — | — | — | |
L1 100% | kimi-k2-thinking | kimi | -27%$0.438/M | -30%$1.75/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | $0.010/request | - | — | — | — | |
L1 100% | moonshotai/Kimi-K2-Thinking | default | -51%$0.294/M | -53%$1.17/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | $1.96/M | $7.83/M | — | — | — | |
L1 100% | Pro/moonshotai/Kimi-K2-Thinking | default | $1.96/M | $7.83/M | — | — | — | |
L1 100% | kimi-k2-thinking-251104 | default | $1.96/M | $7.83/M | — | — | — | |
L1 100% | kimi-k2-thinking | other | -72%$0.167/M Cache read$0.167/M | -58%$1.04/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | -54%$0.274/M | $2.74/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | $1.10/M | $4.38/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | -9%$0.548/M | -12%$2.19/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | -9%$0.548/M | -12%$2.19/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | -9%$0.548/M | -12%$2.19/M | — | — | — | |
L1 100% | kimi-k2-thinking-251104 | default | -9%$0.548/M | -12%$2.19/M | — | — | — | |
L1 100% | kimi-k2-thinking | default | $0.822/M | $3.29/M | — | — | — | |
L1 99% | kimi-k2-thinking | deepseek | -63%$0.219/M | -65%$0.877/M | — | — | — | |
L1 99% | kimi-k2-thinking | default | $100.00/request | - | — | — | — | |
L1 99% | kimi-k2-thinking | default | -9%$0.548/M | -12%$2.19/M | — | — | — | |
L1 99% | kimi-k2-thinking | default | $3.20/M | $12.80/M | — | — | — | |
L1 97% | moonshotai/kimi-k2-thinking | default | $75.00/M | $75.00/M | — | — | — |
