PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8023mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0023mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9923mPERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%53mPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%53mPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%53mPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%53mPERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%53mPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%53mPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%53mPERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%53mPERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%53mPERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%53mPERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%53mPERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%53mPERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%53mPERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%53mPERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%53mPERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%53mPERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%53mPERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%53mPERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%53mPERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%53mPERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%53mPERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%53mPERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%53mPERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%53mPERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%53mPERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%53mPERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%53mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2954mPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3654mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.7554mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.001154mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.0454mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.003854mPRICEz-ai/glm-5.1 cached_input_per_mtok increased from 0.18 to 0.2654mPRICEz-ai/glm-5.1 output_per_mtok increased from 3.03 to 4.4054mPRICEz-ai/glm-5.1 input_per_mtok increased from 0.96 to 1.4054mPRICEtencent/hy4-preview cached_input_per_mtok increased from 0.038 to 0.04254m

Kimi K3 on OpenRouter

#3 of 3 providers for Kimi K3 · #12 of 13 models on OpenRouter · US · EU
Compare with other providers
Score76.2Rel.97.2%Tools100.0%JSON100.0%TTFT674 msP953408 msTok/s90Price$2.70 / $13.50Ctx1M217 results · last 53m ago

Kimi K3 on other providers

ProviderScoreTTFTTok/s$ Out
Cortecs88.0624 ms171$15.43
Together82.6602 ms104$13.50
OpenRouterTHIS PAGE76.2674 ms90$13.50

Other models on OpenRouter

ModelScoreTTFT$ Out
GPT-OSS 120B93.3474 ms$0.17
GPT-OSS 20B92.3656 ms$0.09
Llama 3.3 70B89.4576 ms$0.32
Qwen3-235B86.2766 ms$0.35
DeepSeek V4 Flash85.91059 ms$0.056
Mistral Large 381.5406 ms$1.50
Mistral Medium 3.580.4259 ms$7.50
DeepSeek V4 Pro80.21086 ms$0.42
GLM-5.379.8412 ms$4.40
MiniMax M377.8929 ms$1.20
GLM-5.273.8480 ms$3.99
Kimi K3THIS PAGE72.0674 ms$13.50
GLM-4.759.92259 ms$2.20