{"slug": "deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis", "title": "DeepSeek v4.1 Flash 1017 Scores 45 in Artificial Analysis", "summary": "DeepSeek V4.1 Flash 1017 (Max) scored 45 on the Artificial Analysis Intelligence Index, well above the median of 19 for comparable models, according to Artificial Analysis. The open-weight reasoning model has 552B total parameters with 16B active per token, a 1M-token context window, text and image input, and an MIT license, with weights on Hugging Face. Artificial Analysis priced it at $0.30 per 1M input tokens and $1.20 per 1M output tokens, an average of $0.26 per task, and measured output speed at 230 tokens per second, though it generated 210M tokens on the index versus a median of 140M.", "body_md": "# DeepSeek V4.1 Flash 1017 (Max) Intelligence, Performance & Price Analysis\n\n### Model summary\n\nDeepSeek V4.1 Flash 1017 (Max) is amongst the leading models in intelligence and reasonably priced when comparing to other open weight models of similar size. It's also notably fast, however very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.\n\nDeepSeek V4.1 Flash 1017 (Max) scores 45 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 19). When evaluating the Intelligence Index, it generated 210M tokens, which is very verbose in comparison to the median of 140M.\n\nPricing for DeepSeek V4.1 Flash 1017 (Max) is $0.30 per 1M input tokens (moderately priced, median: $0.43) and $1.20 per 1M output tokens (moderately priced, median: $1.68). On average, it costs $0.26 per task to evaluate DeepSeek V4.1 Flash 1017 (Max) on the Intelligence Index.\n\nAt 230 tokens per second, DeepSeek V4.1 Flash 1017 (Max) is notably fast (78).\n\n| Reasoning | Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist. | \n|---|---|\n| Input modality | Supports: text and image | \n| Output modality | Supports: text | \n| Context window | 1M ~1500 A4 pages of size 12 Arial font | \n| Total parameters | 552B | \n| Active parameters | 16B Number of parameters active per token during inference | \n| License | [MIT](https://opensource.org/license/mit) | \n| Model weights | [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) | \n\nMetrics are compared against models of the same class:\n\n- Non-reasoning models → compared only with other non-reasoning models\n- Reasoning models → compared across both reasoning and non-reasoning\n- Open weights models → compared only with other open weights models of the same size class:\n- Tiny: ≤4B parameters\n- Small: 4B–40B parameters\n- Medium: 40B–150B parameters\n- Large: >150B parameters\n- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:\n- <$0.15 per 1M tokens\n- $0.15–$1 per 1M tokens\n- >$1 per 1M tokens\n\n## Intelligence\n\n### [Artificial Analysis Intelligence Index](https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index)\n\n### Artificial Analysis Intelligence Index by Open Weights / Proprietary\n\n### Intelligence Index vs. Cost per Task\n\nMeasures the performance of models on specific capabilities and industries\n\n### [Artificial Analysis Finance & Accounting Index](https://artificialanalysis.ai/indexes/finance-and-accounting)\n\n### Evaluations\n\n[AA-Briefcase v1.1](https://artificialanalysis.ai/evaluations/aa-briefcase)Updated\n\nAgentic knowledge work, (Elo-500)/2000\n\nKnowledge\n\n1 - hallucination rate\n\nAgentic SaaS workflows\n\n[GDPval-AA v2.1](https://artificialanalysis.ai/evaluations/gdpval-aa)Updated\n\nAgentic real-world work tasks, (Elo-500)/2000\n\nReasoning & knowledge\n\nProfessional document reasoning, All-pass\n\nAgentic coding & terminal use\n\nLong context reasoning\n\n[SciCode](https://artificialanalysis.ai/evaluations/scicode)Under review\n\nCoding\n\n[CritPt](https://artificialanalysis.ai/evaluations/critpt)Under review\n\nPhysics reasoning\n\nAgentic scientific research workflows in a terminal\n\nAgentic software engineering in open-source repositories\n\nQuantitative analysis on spreadsheets & documents\n\n[Harvey LAB-AA v1.1](https://artificialanalysis.ai/evaluations/harvey-lab-aa)Updated\n\nLegal agentic work, Hallucination-Gated All-Pass Rate\n\nAgentic business operations\n\nKubernetes incident root-cause analysis\n\nMedical long context reasoning\n\nVisual reasoning\n\n### AA-Briefcase v1.1Updated\n\n### AA-Briefcase Elo\n\n### AA-Omniscience\n\n### AA-Omniscience Index\n\n## Openness Index\n\n### Artificial Analysis Openness Index: Score\n\n## Intelligence Index Comparisons\n\n### Intelligence Index vs. Cost per Task\n\n## Token Use\n\n### Output Tokens per Intelligence Index Task\n\n## Cost\n\n### Cost per Intelligence Index Task\n\n### Cost to Run Artificial Analysis Intelligence Index\n\n### Pricing: Cache Hit, Input, and Output\n\n## Context Window\n\n### Context Window\n\n## Speed\n\nMeasured by Output Speed (tokens per second)\n\n### Output Speed\n\n### Time per Intelligence Index Task\n\n## Latency\n\nMeasured by Time (seconds) to First Token\n\n### Latency: Time To First Answer Token\n\n## End-to-End Response Time\n\nSeconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed\n\n### End-to-End Response Time\n\n## Model Size (Open Weights Models Only)\n\n### Model Size: Total and Active Parameters\n\n## Frequently Asked Questions\n\nCommon questions about DeepSeek V4.1 Flash 1017 (Max)\n\nDeepSeek V4.1 Flash 1017 (Max) was released on October 17, 2026.\n\nDeepSeek V4.1 Flash 1017 (Max) was created by DeepSeek.\n\nDeepSeek V4.1 Flash 1017 (Max) scores 45 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 19).\n\nDeepSeek V4.1 Flash 1017 (Max) generates output at 230.4 tokens per second (based on DeepSeek's API), which is well above average compared to other open weight models of similar size (median: 77.9 t/s).\n\nDeepSeek V4.1 Flash 1017 (Max) has a time to first token (TTFT) of 1.08s (based on DeepSeek's API), which is very competitive compared to other open weight models of similar size (median: 1.69s).\n\nDeepSeek V4.1 Flash 1017 (Max) costs $0.30 per 1M input tokens (better than average, median: $0.43) and $1.20 per 1M output tokens (better than average, median: $1.68), based on DeepSeek's API.\n\nDeepSeek V4.1 Flash 1017 (Max) costs $0.30 per 1M input tokens and $1.20 per 1M output tokens (based on DeepSeek's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.18 per 1M tokens. Pricing may vary by provider. [Compare provider pricing](https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers)\n\nWhen evaluated on the Intelligence Index, DeepSeek V4.1 Flash 1017 (Max) generated 210M output tokens, which is at the higher end compared to other open weight models of similar size (median: 140M).\n\nYes, DeepSeek V4.1 Flash 1017 (Max) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.\n\nDeepSeek V4.1 Flash 1017 (Max) supports text and image input.\n\nDeepSeek V4.1 Flash 1017 (Max) supports text output.\n\nYes, DeepSeek V4.1 Flash 1017 (Max) supports image input and can analyze, describe, and answer questions about images.\n\nYes, DeepSeek V4.1 Flash 1017 (Max) is multimodal. It can process text and image input and generate text output.\n\nDeepSeek V4.1 Flash 1017 (Max) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.\n\nYes, DeepSeek V4.1 Flash 1017 (Max) is open weights. The model weights are publicly available and can be downloaded for self-hosting.\n\nDeepSeek V4.1 Flash 1017 (Max) has 552 billion parameters (16 billion active).\n\nDeepSeek V4.1 Flash 1017 (Max) is a Mixture of Experts (MoE) model with 552 billion total parameters, but only 16 billion active parameters are used during inference.\n\nDeepSeek V4.1 Flash 1017 (Max) is released under the MIT license. This license allows commercial use. [View license](https://opensource.org/license/mit)\n\nDeepSeek V4.1 Flash 1017 (Max) achieves a score of 45 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.\n\nYes, DeepSeek V4.1 Flash 1017 (Max) is available via API through 5 providers. [Compare API providers](https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers)\n\nDeepSeek V4.1 Flash 1017 (Max) is available through 5 API providers. [Compare providers](https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017/providers)", "url": "https://wpnews.pro/news/deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis", "canonical_source": "https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017", "published_at": "2026-10-19 04:41:46+00:00", "updated_at": "2026-10-19 04:48:35.774163+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research", "machine-learning"], "entities": ["DeepSeek", "DeepSeek V4.1 Flash 1017", "Artificial Analysis", "Hugging Face"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis", "markdown": "https://wpnews.pro/news/deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis.md", "text": "https://wpnews.pro/news/deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis.txt", "jsonld": "https://wpnews.pro/news/deepseek-v4-1-flash-1017-scores-45-in-artificial-analysis.jsonld"}}