| Model | Context | Input / 1M | Output / 1M | Cache Read / 1M |
|---|---|---|---|---|
| MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5 |
262K | $0.500 | $2.50 | $0.150 |
| MoonshotAI: Kimi K2 0711 moonshotai/kimi-k2 |
131K | $0.570 | $2.30 | — |
| MoonshotAI: Kimi K2 0905 moonshotai/kimi-k2-0905 |
262K | $0.600 | $2.50 | — |
| MoonshotAI: Kimi K2 Thinking moonshotai/kimi-k2-thinking |
262K | $0.600 | $2.50 | $0.150 |
| MoonshotAI: Kimi K2.7 Code moonshotai/kimi-k2.7-code |
262K | $0.600 | $3.00 | $0.120 |
| MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6 |
262K | $0.650 | $3.41 | $0.150 |
| MoonshotAI: Kimi K3.1 Pro (batch) moonshotai/kimi-k3.1-pro:batch |
1.0M | $0.372 | $5.58 | $0.100 |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro |
1.0M | $0.253 | $8.80 | $0.180 |
| MoonshotAI: Kimi K3 moonshotai/kimi-k3 |
1.0M | $0.192 | $16.00 | $0.182 |
| MoonshotAI: Kimi K3 (batch) moonshotai/kimi-k3:batch |
1.0M | $2.28 | $11.40 | $0.228 |
Recommended AI & GPU Infrastructure
Best for H100 / A100 / 4090
Launch GPU on RunPod →
RunPod Cloud GPUs
Spin up on-demand H100, A100, L40S, and RTX 4090 pods or serverless vLLM endpoints in seconds.
Predictable Cloud Infra
Try DigitalOcean →
DigitalOcean GPU Droplets
Deploy AI inference APIs, vector databases, and GPU droplets with simple monthly billing.
1 API Key · 470+ Models
Get Unified API Key →
OpenRouter Unified API
Switch between Gemini, Claude, GPT, DeepSeek, and Llama with one OpenAI-compatible key.