GoKawiilDeepSeek V4.1 Flash 1017 (Max) debuts with 1M-token context and strong benchmark score
DeepSeek has released V4.1 Flash 1017 (Max), a multimodal model accepting text and image input and producing text output, with a 1 million token context window. The model scored 45 on the Artificial Analysis Intelligence Index, well above the comparable median of 19, while running at 230 tokens per second.
GoKawiil's interpretation of the reporting above, not reported fact.
The combination of above-average intelligence scores and moderate pricing ($0.30/$1.20 per million input/output tokens) could make the model an attractive option for developers weighing cost against capability among open-weight models. Its high verbosity, generating 210M tokens during evaluation versus a 140M median, suggests users may face higher per-task costs or slower practical throughput despite its raw speed rating.
- Scores 45 on the Artificial Analysis Intelligence Index, above the median of 19 for comparable models
- Priced at $0.30 per 1M input tokens and $1.20 per 1M output tokens, both below category medians
- Runs at 230 tokens per second but is notably verbose, raising average cost per evaluation task to $0.26
Source: artificialanalysis.ai, 2026-10-19
Published there as: “DeepSeek V4.1 Flash 1017 (Max)”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.