Models / DeepSeek-V4-Flash (0731)

DeepSeek

DeepSeek-V4-Flash (0731)

Early evidence, 10 results from 2 sources, on 3 use cases. DeepSeek-V4-Flash (0731) 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 $0.20.

Superseded. DeepSeek-V4.1-Flash-1017 is DeepSeek's newer model in this line, at $0.52 blended: see DeepSeek-V4.1-Flash-1017.

Results 19 Nov 2026 · 10 results · 2 sources

Test DeepSeek-V4-Flash (0731) on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.13 in · $0.40 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
34.3
Artificial Analysis, at max reasoning
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
DeepSeek, based in China
Weights published
Released
31 Jul 2026 (Artificial Analysis)
1,048,576 tokens of context

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 42nd of 185Claude Opus 5.5 – $0.20 blended, 17th percentilecheapest: Mistral Nemo –
Models priced under $0.25 per million tokens 5th of 41Claude Haiku 5.5 – sets this group –
Models with similar intelligence sets this group – $0.20 blended, 6th percentilecheapest: MiMo-V2.6-Flash –
Models from developers based in China 13th of 75MiMo-V2.6-Pro – $0.20 blended, 13th percentilecheapest: Qwen3.5-9B –
Open-weights models 14th of 104MiMo-V2.6-Pro – $0.20 blended, 25th percentilecheapest: Mistral Nemo –

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 under $0.25 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 43rd of 159 available · 4th of 37 at its price
BenchmarkDeepSeek-V4-Flash (0731)Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 12.1% 37th 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 39.4% 19th 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 Not measured
  • APEX-Agents: has not measured this model.
  • 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 47th of 187 available · 3rd of 41 at its price
BenchmarkDeepSeek-V4-Flash (0731)Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 34.3 42nd of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 38.6% 49th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 90.8% 33rd of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality Not measured
  • Arena (formerly LMArena): has not measured this model.
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 105th of 139 available · 19th of 30 at its price
BenchmarkDeepSeek-V4-Flash (0731)Rank among availableBest available
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 33.6% 50th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): 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-Flash (0731) at $0.20 blended, Intelligence Index 34.3. "Similar intelligence" means within 4 points or better.

Where to run it

27 hosts on OpenRouter at the standard service tier, with a median of $0.20 blended per million tokens; quantisation where the host states it: FP4, FP8, NVFP4, FP32. Cheapest first.

HostQuantisationInputOutputBlended
RelaceFP4$0.07$0.14$0.09
DeepInfraFP8$0.06$0.18$0.09
WaferNVFP4$0.04$0.30$0.11
Rekanot stated$0.10$0.28$0.15
DigitalOceannot stated$0.12$0.24$0.15
BaseTenFP8$0.13$0.26$0.16
BaseTenFP32$0.13$0.26$0.16
Venicenot stated$0.13$0.26$0.16

Other service tiers, not counted above: Wafer fast $0.14 in, $0.23 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 19 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-Flash (0731)Claude Haiku 5.5
most intelligent at under $0.25 per million tokens
MiMo-V2.6-Flash
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $0.20 $0.20$0.18$8.00$0.54
Tokens a second – 240469643
Intelligence Index 34.3 43.437.957.646.3
Spring Prompt overall – 38–80–
Rank among available models, by use case
Product listings – 23rd–16th–
Decks from an analysis – 19th–8th–
User surveys – 9th–5th–
Marketing planning – 33rd–11th–
Agents and tool use 43rd of 159 28th42nd3rd23rd
Professional work – ––3rd–
Reasoning and knowledge 47th of 187 25th55th1st13th
Writing – –56th5th23rd
Sticking to the facts 105th of 139 –46th3rd10th
Speed under pressure – 24th–––

Shaded figures are better than DeepSeek-V4-Flash (0731)'s. A dash means no result.

Where it has been measured

2nd cheapest of the 17 models with similar intelligence. 5th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the top quarter (by percentile) for reasoning and knowledge, and agents and tool use.

Artificial Analysis lists it but has not published a speed for it yet

Every result

10 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 9 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 69.1 55 of 187 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 34.3 91 of 413 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 90.8% 56 of 360 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 38.6% 98 of 419 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 79.7% 86 of 407 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 50.3% 109 of 205 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 78.7% 50 of 188 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 12.1% 91 of 204 DeepSeek-V4-Flash (0731, max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 39.4% 34 of 175 DeepSeek-V4-Flash (0731, 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 33.6% 56 of 85 DeepSeek-V4-Flash (0731, max reasoning) 27 Aug 2026

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

Will DeepSeek-V4-Flash (0731) 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.