Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and the post-trained successor to Kimi K3. It is available via OpenRouter. The price listed here is the OpenRouter listed price, checked Nov 18, 2026: $0.24 per million input tokens and $8.40 per million output tokens (exact OpenRouter rates: $0.0000002403/$0.0000084023 per token). Data Source: OpenRouter listing. Data Confidence: Partial.
Kimi K3.1 Pro supports a 1,048,576-token context window and a maximum output of 943,718 tokens — one of the largest output limits among frontier models. It supports vision input, function calling, and streaming. It is classified as a reasoning model and is open-weight.
Within the Kimi K3 family, K3.1 Pro is the successor to Kimi K3 ($2.00/$8.00 via Moonshot AI direct). The multimodal input support and open-weight availability distinguish K3.1 Pro from its predecessor.
Data source: OpenRouter listing, checked Nov 18, 2026. Data Confidence: Partial — throughput, latency, and benchmark scores are not available for this model at this time. The OpenRouter listed price may differ from Moonshot AI's direct API pricing.
Kimi K3.1 Pro is suited to multimodal reasoning tasks, long-context analysis, and applications that benefit from open-weight availability. Its low input price of $0.24/1M makes it cost-effective for high-volume input workloads despite the higher output rate.
Input price vs 143 frontier models tracked. Avg: $5.58/1M.
| Model ID | kimi-k3-1-pro |
| Provider | Moonshot AI |
| Model Family | Kimi K3 |
| Tier | Frontier |
| Context Window | 1,048,576 tokens (1.0M) |
| Max Output Tokens | 943,718 tokens |
| Input Price | $0.24 / 1M tokens |
| Output Price | $8.4 / 1M tokens |
| Cached Input Price | Not available |
| Throughput | — |
| Latency (P50) | — |
| Intelligence Score | — |
| LiveBench Score | — |
| Cost per Task (LiveBench) | — |
| Data Confidence | Partial |
| HLE Score | — |
| GPQA Diamond | — |
| SWE-bench Score | — |
| OSWorld Score | — |
| BrowseComp Score | — |
| Terminal-Bench Score | — |
| AutoBench Score | — |
| Parameters | — |
| Vision Support | Yes |
| Function Calling | Yes |
| Streaming | Yes |
| Reasoning Model | Yes |
| Open Weights | Yes |
| Data Source | Static (verified) |
| Last Updated | 2026-11-18 |
Self-hosting kimi-k3-1-pro? These GPUs are well-matched for this model's compute and memory requirements.