Models / DeepSeek-V4-Pro (0813)

DeepSeek

DeepSeek-V4-Pro (0813)

DeepSeek-V4-Pro (0813) is best for reasoning and knowledge, and agents and tool use; a strong pick at a modest price. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $1.98.

Results 16 Nov 2026 · 31 results · 4 sources

Test DeepSeek-V4-Pro (0813) on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.32 in · $3.96 out
DeepSeek's list price, 10 Nov 2026 · compare prices$0.04 cached input
Speed
96 tokens a second; on its test prompt the answer starts after 21.9 s, thinking time included
Artificial Analysis, on its usual API, at max reasoning; 93–96 across 2 settings
Intelligence Index
36.0
Artificial Analysis, at max reasoning; 20.4–36.0 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
DeepSeek, based in China
Weights published
Released
13 Aug 2026
1,048,576 tokens of context
Pricing and availability
Half price off-peak ($0.66 / $1.98)

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 40th of 185Claude Opus 5.5 – $1.98 blended, 67th percentilecheapest: Mistral Nemo 38th of 65Nemotron 3.5 Super VL
Models priced $1–3 per million tokens 6th of 34Muse Spark 1.3 – sets this group 4th of 9Muse Spark 1.3
Models with similar intelligence sets this group – $1.98 blended, 33rd percentilecheapest: MiMo-V2.6-Flash 6th of 10DeepSeek-V4.1-Flash
Models writing 50–100 tokens a second 9th of 21Claude Opus 5.5 – $1.98 blended, 60th percentilecheapest: Granite 4.2 8B sets this group
Models from developers based in China 11th of 75MiMo-V2.6-Pro – $1.98 blended, 90th percentilecheapest: Qwen3.5-9B 10th of 23DeepSeek-V4.1-Flash
Open-weights models 12th of 104MiMo-V2.6-Pro – $1.98 blended, 91st percentilecheapest: Mistral Nemo 22nd of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 39th of 159 available · 7th of 31 at its price
BenchmarkDeepSeek-V4-Pro (0813)Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 14.1% 32nd of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 78.7% 24th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 39.6% 17th of 104 Grok 4.6 50.7%
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 29th of 51 available · 3rd of 12 at its price
BenchmarkDeepSeek-V4-Pro (0813)Rank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 47.3% 24th of 37 Claude Sonnet 5.5 75.5%
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 35th of 187 available · 5th of 35 at its price
BenchmarkDeepSeek-V4-Pro (0813)Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 36.0 40th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 41.0% 41st of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 92.8% 15th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 38th of 169 available · 9th of 28 at its price
BenchmarkDeepSeek-V4-Pro (0813)Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,464 37th of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 44th of 139 available · 6th of 26 at its price
BenchmarkDeepSeek-V4-Pro (0813)Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,454 43rd of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 52.9% 20th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against DeepSeek-V4-Pro (0813) at $1.98 blended, Intelligence Index 36.0. "Similar intelligence" means within 4 points or better.

Where to run it

24 hosts on OpenRouter at the standard service tier, with a median of $1.80 blended per million tokens; quantisation where the host states it: MXFP4, FP8, FP4. Cheapest first.

HostQuantisationInputOutputBlended
Alibabanot stated$0.58$1.74$0.87
Alibabanot stated$0.66$1.98$0.99
DeepSeeknot stated$0.66$1.98$0.99
StreamLakenot stated$0.66$1.98$0.99
WaferMXFP4$0.11$4.44$1.19
WaferMXFP4$0.28$4.30$1.29
Phalanot stated$0.96$2.88$1.44
NovitaFP8$0.99$2.97$1.48

Other service tiers, not counted above: Parasail fast $1.98 in, $5.94 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 16 dearer hosts are left out.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

DeepSeek-V4-Pro (0813)Muse Spark 1.3
most intelligent at $1–3 per million tokens
MiMo-V2.6-Flash
cheapest with similar intelligence
DeepSeek-V4.1-Flash
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $1.98 $2.00$0.18$0.52$8.00
Tokens a second 96 2544636996
Intelligence Index 36.0 48.137.939.557.6
Spring Prompt overall – 59–5182
Rank among available models, by use case
Product listings – 17th–15th13th
Decks from an analysis – 25th––7th
User surveys – –––4th
Marketing planning – 25th––9th
Agents and tool use 39th of 159 13th42nd31st3rd
Professional work 29th of 51 8th––3rd
Reasoning and knowledge 35th of 187 11th55th42nd1st
Writing 38th of 169 7th56th29th5th
Sticking to the facts 44th of 139 11th46th23rd3rd
Speed under pressure – 33rd–––

Shaded figures are better than DeepSeek-V4-Pro (0813)'s. A dash means no result.

Where it has been measured

6th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the top quarter (by percentile) for reasoning and knowledge, agents and tool use, and writing.

Every result

31 published results from 4 sources, each in the source's own units, with the configuration that produced it.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 47.3% 25 of 39 DeepSeek-V4-Pro (0813) 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better -0.02
-0.06–0.02
33 of 50 DeepSeek-V4-Pro (0813, high reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better 0.02
-0.04–0.08
26 of 50 DeepSeek-V4-Pro (0813, high reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.01
-0.01–0.03
27 of 50 DeepSeek-V4-Pro (0813, high reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.00
22 of 50 DeepSeek-V4-Pro (0813, high reasoning, arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,454
1,448–1,459
58 of 182 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,467
1,453–1,481
44 of 406 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,445
1,431–1,458
53 of 411 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,484
1,466–1,503
65 of 363 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,461
1,451–1,471
48 of 413 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,464
1,458–1,471
56 of 413 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,454
1,442–1,466
47 of 412 DeepSeek-V4-Pro (0813, high reasoning) 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 18 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 68.8 56 of 187 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 36.0 83 of 413 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 20.4 206 of 413 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 92.8% 28 of 360 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 41.0% 81 of 419 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 10.6% 274 of 419 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 80.3% 70 of 407 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 50.7% 278 of 407 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 95.9 73 of 137 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 93.0 77 of 137 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 51.0% 102 of 205 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 39.9% 165 of 205 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 78.7% 50 of 188 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 14.1% 81 of 204 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 1.5% 129 of 204 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 21.9 86 of 137 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 1.18 32 of 137 DeepSeek-V4-Pro (0813, no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 39.6% 32 of 175 DeepSeek-V4-Pro (0813, max reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 52.9% 20 of 85 DeepSeek-V4-Pro (0813, max reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

Will DeepSeek-V4-Pro (0813) work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.