DeepSeek V4.1 Flash
DeepSeek V4.1 Flash model for reasoning and agentic coding
Shogo Agent Index
Estimated#35 of 9251.2range 37.1–65.2 · 13% of weight measured
Agentic coding
57
estimated
Long-horizon autonomy
62
estimated
Knowledge-work agents
39
52% measured
Computer use
40
estimated
Security & context learning
51
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 80 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 79 | |
| DeepSWE | est. | 6% | predicted 55 | |
| FrontierSWE | est. | 5% | predicted 21 | |
| CursorBench | est. | 4% | predicted 40 | |
| GSO-Bench | est. | 4% | predicted 36 | |
| METR Time Horizons | est. | 10% | predicted 77 | |
| Vending-Bench 2 | est. | 6% | predicted 58 | |
| PostTrainBench | est. | 4% | predicted 27 | |
| APEX-Agents | 39.5% | 8% | source | |
| GDPval | est. | 7% | predicted 51 | |
| Remote Labor Index | 9.6% | 5% | source | |
| DeepResearch Bench | est. | 5% | predicted 49 | |
| OSWorld 2.0 | est. | 6% | predicted 13 | |
| OSWorld | est. | 4% | predicted 81 | |
| Cybench | est. | 5% | predicted 79 | |
| CL-bench | est. | 5% | predicted 23 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 94.5% | source |
| ARC-AGI-2 | Reasoning | 72.9% | source |
| Chess Puzzles | Reasoning | 48.0% | source |
| CritPt | Reasoning | 14.3% | source |
| DTBench | Knowledge | 89.9% | source |
| FrontierCode | Coding | 43.9% | devin-cli |
| FrontierMath Tiers 1-3 | Math | 67.4% | source |
| FrontierMath Tier 4 | Math | 26.8% | source |
| GPQA Diamond | Reasoning | 89.8% | source |
| LMCA | Knowledge | 47.0% | source |
| MirrorCode | Coding | 64.4% | source |
| OTIS Mock AIME | Math | 98.3% | source |
| ProofBench | Math | 54.0% | source |
| SciCode | Coding | 51.9% | source |
| SimpleBench | Reasoning | 66.7% | source |
| SimpleQA Verified | Knowledge | 42.9% | source |
| WebDev Arena | Coding | 1614 | source |
| WeirdML v3 | Coding | 5.9% | opencode |
API hosts
Live prices and uptime for every host serving DeepSeek V4.1 Flash via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| DeepInfra | $0.11 | $0.34 | $0.003 | $0.030 | 100.0% | fp8 |
| DeepInfra | $0.14 | $0.42 | $0.004 | $0.040 | 100.0% | fp8 |
| Novita | $0.12 | $0.48 | $0.002 | $0.040 | 100.0% | fp8 |
| Relace | $0.12 | $0.50 | $0.003 | $0.040 | 100.0% | fp4 |
| River | $0.12 | $0.48 | $0.002 | $0.040 | 99.9% | — |
| CoreWeave | $0.13 | $0.65 | $0.002 | $0.050 | 100.0% | fp8 |
| Fireworks | $0.15 | $0.60 | $0.003 | $0.050 | 98.3% | — |
| InferenceNet | $0.10 | $0.60 | $0.008 | $0.050 | 100.0% | fp8 |
| InferenceNet | $0.10 | $0.60 | $0.008 | $0.050 | 100.0% | fp8 |
| OpenInference | $0.060 | $0.90 | $0.002 | $0.050 | 99.8% | fp4 |
| Reka | $0.12 | $0.64 | $0.008 | $0.050 | 100.0% | — |
| StreamLake | $0.15 | $0.59 | $0.003 | $0.050 | 100.0% | fp8 |
| Wafer | $0.051 | $0.57 | $0.018 | $0.050 | 100.0% | mxfp4 |
| Alibaba | $0.18 | $0.72 | $0.004 | $0.060 | 100.0% | — |
| AtlasCloud | $0.14 | $0.54 | $0.013 | $0.060 | 100.0% | fp8 |
| Cohere | $0.20 | $0.66 | $0.003 | $0.060 | 100.0% | fp8 |
| GMICloud | $0.18 | $0.72 | $0.004 | $0.060 | 100.0% | fp8 |
| DeepInfra | $0.21 | $0.63 | $0.006 | $0.070 | 99.9% | fp8 |
| Wafer | $0.19 | $0.65 | $0.012 | $0.070 | 100.0% | mxfp4 |
| Cloudflare | $0.10 | $0.90 | $0.030 | $0.080 | 99.6% | — |
| DigitalOcean | $0.23 | $0.90 | $0.006 | $0.080 | 99.9% | — |
| Ionstream | $0.20 | $0.70 | $0.020 | $0.080 | 100.0% | — |
| Baidu | $0.30 | $1.20 | $0.006 | $0.10 | 100.0% | fp8 |
| Crusoe | $0.29 | $1.20 | $0.007 | $0.10 | 98.0% | fp8 |
| Fireworks | $0.30 | $1.20 | $0.006 | $0.10 | 100.0% | — |
| Makora | $0.26 | $1.17 | $0.006 | $0.10 | 90.5% | fp8 |
| Parasail | $0.30 | $1.20 | $0.006 | $0.10 | 100.0% | fp8 |
| SiliconFlow | $0.30 | $1.20 | $0.006 | $0.10 | 100.0% | fp8 |
| Together | $0.30 | $1.20 | $0.006 | $0.10 | 100.0% | — |
| BaseTen | $0.30 | $1.20 | $0.007 | $0.11 | 100.0% | — |
| BaseTen | $0.30 | $1.20 | $0.007 | $0.11 | 100.0% | — |
| Mancer 2 | $0.21 | $0.75 | $0.050 | $0.11 | 100.0% | fp8 |
| Nebius | $0.30 | $1.20 | $0.010 | $0.11 | 100.0% | fp8 |
| Venice | $0.30 | $1.20 | $0.007 | $0.11 | 100.0% | fp8 |
| $0.30 | $1.20 | $0.030 | $0.12 | 100.0% | — | |
| Modal | $0.30 | $1.20 | $0.030 | $0.12 | 100.0% | — |
| Fireworks | $0.45 | $1.80 | $0.009 | $0.16 | 100.0% | — |
| Parasail | $0.45 | $1.80 | $0.009 | $0.16 | 100.0% | fp8 |
| Venice | $3.00 | $12.00 | $0.060 | $1.05 | 100.0% | fp8 |