Kimi K3.1 Pro
Multimodal Kimi model with a 1M-token context window and always-on reasoning, for coding, 3D creation and financial research
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
67
estimated
Long-horizon autonomy
70
estimated
Knowledge-work agents
49
32% measured
Computer use
49
estimated
Security & context learning
56
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 84 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 88 | |
| DeepSWE | est. | 6% | predicted 66 | |
| FrontierSWE | est. | 5% | predicted 34 | |
| CursorBench | est. | 4% | predicted 46 | |
| GSO-Bench | est. | 4% | predicted 53 | |
| METR Time Horizons | est. | 10% | predicted 81 | |
| Vending-Bench 2 | est. | 6% | predicted 76 | |
| PostTrainBench | est. | 4% | predicted 32 | |
| APEX-Agents | 65.5% | 8% | source | |
| GDPval | est. | 7% | predicted 59 | |
| Remote Labor Index | est. | 5% | predicted 9 | |
| DeepResearch Bench | est. | 5% | predicted 50 | |
| OSWorld 2.0 | est. | 6% | predicted 22 | |
| OSWorld | est. | 4% | predicted 89 | |
| Cybench | est. | 5% | predicted 87 | |
| CL-bench | est. | 5% | predicted 26 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Chess Puzzles | Reasoning | 45.0% | source |
| CritPt | Reasoning | 24.6% | source |
| DTBench | Knowledge | 93.3% | source |
| FrontierMath Tiers 1-3 | Math | 78.2% | source |
| FrontierMath Tier 4 | Math | 65.9% | source |
| GPQA Diamond | Reasoning | 94.2% | source |
| LMCA | Knowledge | 57.6% | source |
| MirrorCode | Coding | 43.3% | source |
| OTIS Mock AIME | Math | 100.0% | source |
| ProofBench | Math | 91.0% | source |
| SciCode | Coding | 60.8% | source |
| SimpleQA Verified | Knowledge | 62.2% | source |
| WeirdML v3 | Coding | 9.9% | kimi_code |
API hosts
Live prices and uptime for every host serving Kimi K3.1 Pro via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Decart | $1.20 | $6.00 | $0.12 | $0.55 | 100.0% | mxfp4 |
| Relace | $0.24 | $8.40 | $0.20 | $0.60 | 100.0% | fp4 |
| Wafer | $0.25 | $8.80 | $0.18 | $0.60 | 100.0% | mxfp4 |
| Sail Research | $1.04 | $9.35 | $0.19 | $0.75 | 100.0% | fp4 |
| Sail Research | $1.40 | $9.35 | $0.19 | $0.80 | 100.0% | fp4 |
| Wafer | $1.80 | $9.00 | $0.18 | $0.83 | 100.0% | mxfp4 |
| InferenceNet | $1.80 | $9.00 | $0.20 | $0.85 | 100.0% | mxfp4 |
| InferenceNet | $1.80 | $9.00 | $0.20 | $0.85 | 100.0% | mxfp4 |
| AkashML | $1.75 | $10.00 | $0.18 | $0.87 | 100.0% | fp4 |
| DeepInfra | $1.90 | $9.50 | $0.19 | $0.88 | 99.8% | bf16 |
| Makora | $2.00 | $9.49 | $0.20 | $0.90 | 97.1% | — |
| Alibaba | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | — |
| DigitalOcean | $2.00 | $10.00 | $0.20 | $0.92 | 99.9% | — |
| Fireworks | $2.00 | $10.00 | $0.20 | $0.92 | 98.1% | — |
| Modal | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | mxfp4 |
| Moonshot AI | $2.00 | $10.00 | $0.20 | $0.92 | 99.9% | mxfp4 |
| Nebius | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | fp4 |
| Parasail | $2.00 | $10.00 | $0.20 | $0.92 | 100.0% | fp4 |
| PrimaLabs | $2.00 | $10.00 | $0.20 | $0.92 | 99.9% | mxfp4 |
| River | $2.00 | $10.00 | $0.20 | $0.92 | 99.6% | — |
| Together | $2.00 | $10.00 | $0.20 | $0.92 | 99.9% | — |
| InferenceNet | $2.70 | $13.50 | $0.27 | $1.25 | 100.0% | mxfp4 |
| InferenceNet | $2.70 | $13.50 | $0.27 | $1.25 | 100.0% | mxfp4 |
| Morph | $1.38 | $20.62 | $0.44 | $1.53 | 98.6% | fp8 |
| Amazon Bedrock | $4.00 | $20.00 | $0.20 | $1.69 | 100.0% | — |
| Moonshot AI | $4.00 | $20.00 | $0.20 | $1.69 | 98.8% | mxfp4 |
| Amazon Bedrock | $4.40 | $22.00 | $0.22 | $1.85 | 100.0% | — |