AI RankingAI Adoption Rankings
Third-partyHacker News ·2026-11-14 ·8 pts

DeepSeek V4 Pro 0813

Photo: Guido from Berlin / CC BY 2.0 · Wikimedia Commons (cropped to 560x315)

Released August 2026

DeepSeek V4 Pro 0813 (Max) is below average in intelligence and somewhat expensive when comparing to other open weight models of similar size. It's also slower than average per task and somewhat verbose. The model supports text input, outputs text, and has a 1M tokens context window.

DeepSeek V4 Pro 0813 (Max) scores 23 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 23). When evaluating the Intelligence Index, it generated 119M tokens, which is somewhat verbose in comparison to the median of 104M.

Pricing for DeepSeek V4 Pro 0813 (Max) is $1.32 per 1M input tokens (expensive, median: $0.43) and $3.96 per 1M output tokens (expensive, median: $1.84). On average, it costs $1.77 per task to evaluate DeepSeek V4 Pro 0813 (Max) on the Intelligence Index.

At 18.1 minutes per Intelligence Index task, DeepSeek V4 Pro 0813 (Max) is slower than average compared with the median of 13.5 minutes for comparable models (lower is better).

Metrics are compared against models of the same class:

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1 . See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1 . See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1 . See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

Agentic knowledge work, Elo

1 - hallucination rate

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Agentic business operations

Agentic real-world work tasks, Elo

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1 . See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

DeepSeek V4.1 Flash 1017

Highest Intelligence

DeepSeek V4 Flash Vision

Common questions about DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 was released on August 13, 2026.

DeepSeek V4 Pro 0813 was created by DeepSeek.

DeepSeek V4 Pro 0813 has 3 effort levels: max, high, and non-reasoning. DeepSeek V4 Pro 0813 scores 23 (max), 21 (high), and 13 (non-reasoning) on the Artificial Analysis Intelligence Index. DeepSeek V4 Pro 0813 (Max) is below average among other open weight models of similar size (median: 23).

DeepSeek V4 Pro 0813 takes 18.1 minutes (max), 15.1 minutes (high), and 13.3 minutes (non-reasoning) per Intelligence Index task (based on DeepSeek's API; lower is better). DeepSeek V4 Pro 0813 (Max) is slower than average compared to other open weight models of similar size (median: 13.5 minutes).

DeepSeek V4 Pro 0813 has a time to first answer token of 51.48s (max), 57.23s (high), and 2.45s (non-reasoning) (based on DeepSeek's API). DeepSeek V4 Pro 0813 (Max)'s time to first answer token is at the higher end compared to other open weight models of similar size (median: 19.60s).

DeepSeek V4 Pro 0813 costs $1.32 per 1M input tokens (at the higher end, median: $0.43) and $3.96 per 1M output tokens (at the higher end, median: $1.84), based on DeepSeek's API.

DeepSeek V4 Pro 0813 costs $1.32 per 1M input tokens and $3.96 per 1M output tokens (based on DeepSeek's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.69 per 1M tokens. Pricing may vary by provider. Compare provider pricing

When evaluated on the Intelligence Index, DeepSeek V4 Pro 0813 generated 119M output tokens (max), 98.4M output tokens (high), and 58.3M output tokens (non-reasoning). DeepSeek V4 Pro 0813 (Max)'s output token count is somewhat higher than average compared to other open weight models of similar size (median: 104M).

Yes, DeepSeek V4 Pro 0813 (max and high) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, DeepSeek V4 Pro 0813 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

DeepSeek V4 Pro 0813 supports text input.

DeepSeek V4 Pro 0813 supports text output.

No, DeepSeek V4 Pro 0813 does not support image input. It can only process text.

No, DeepSeek V4 Pro 0813 is not multimodal. It only supports text input.

DeepSeek V4 Pro 0813 has a context window of 1M tokens. This determines how much text and conversation history the model can process in a single request.

Yes, DeepSeek V4 Pro 0813 is open weights. The model weights are publicly available and can be downloaded for self-hosting.

DeepSeek V4 Pro 0813 has 1.6T parameters (49B active).

DeepSeek V4 Pro 0813 is a Mixture of Experts (MoE) model with 1.6T total parameters, but only 49B active parameters are used during inference.

DeepSeek V4 Pro 0813 is released under the MIT license. This license allows commercial use. View license

DeepSeek V4 Pro 0813 achieves a score of 23 (max), 21 (high), and 13 (non-reasoning) on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across knowledge work, coding, science, and general knowledge.

Yes, DeepSeek V4 Pro 0813 is available via API through 8 providers. Compare API providers

DeepSeek V4 Pro 0813 is available through 8 API providers. Compare providers

Read the original artificialanalysis.ai ↗

Headline, image and article body come from Hacker News; all rights remain with it. Reproduced unmodified for indexing — please refer to the original.

“Deepseek V4 PRO” in our rankings: View the boards →
Our data and derived results are licensed CC BY 4.0. Copyright of indexed items belongs to their respective sources.