DeepSeek V4 Pro 0813 vs DeepSeek V4.1 Flash
At a Glance
| Compare |  DeepSeek V4 Pro 0813DeepSeek | DeepSeek V4.1 FlashDeepSeek |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #20 of 4665.0 score · 3/3 sources · complete | UnrankedNot in the 46-model eligible cohort |
| CostLower is better · Published-token output estimate | #20 of 44$0.094 per LiveBench case | #5 of 44$0.022 per LiveBench case |
| EfficiencyHigher is better · MM Efficiency v1.5 | #14 of 3857.4 score · 3/3 sources · complete | UnrankedNot in the 38-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $1.30Deepinfra ↗ · Sep 22, 2026 | $0.15DeepSeek ↗ · Sep 10, 2026 |
| Output priceFrom · USD / 1M tokens | $2.60Deepinfra ↗ · Sep 22, 2026 | $0.60Deepinfra ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 1,049K | 1,049K |
| Model facts checked | Sep 3, 2026View model evidence → | Sep 10, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4.1-Flash |
|---|---|---|
| LMArena Agent Arenaagent-2026-09-15-d25aabda0010 · outcome_score · statistical tie | 4.1499% of row best · score · DeepSeek V4 Pro (High) (0813); 95% CI [3.35150819, 4.93122185]; sessions 47602; observations 4132769; rank 16 | 4.88100% of row best · score · Deepseek V4.1 Flash (Max); 95% CI [3.54852933, 6.21109128]; sessions 20080; observations 2295632; rank 12 |
| LiveBench2026-06-25 · overall · leader | 81.9198% of row best · percent · deepseek-v4-pro-0813 · 36,339 output tokens / case | 83.20100% of row best · percent · deepseek-v4.1-flash-max · 36,355 output tokens / case |
| ToneBench2026-09-11-10-task-4ef099199c9c · overall_score · unverified | 84.6896% of row best · points · DeepSeek V4 Pro 0813 (max) · 18,462 output tokens / case | 88.03100% of row best · points · DeepSeek V4.1 Flash (max) · 18,199 output tokens / case |
| Overall ResultCounted from the protocol-matched rows above · 1 tie | 0 benchmark winsNo overall winner | 1 benchmark winNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | DeepSeek-V4-Pro-0813 | DeepSeek-V4.1-Flash |
|---|---|---|
| Developer | DeepSeek | DeepSeek |
| Family | Deepseek V4 Pro | Deepseek V4 1 |
| Model | DeepSeek-V4-Pro-0813 | DeepSeek-V4.1-Flash |
| Version | DeepSeek-V4-Pro-0813 | DeepSeek-V4.1-Flash |
| Lifecycle | active | active |
| Released | 2026-08-13 | 2026-09-10 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 1,049K | 1,049K |
| Total parameters | 1.6T | 763.2B |
| Active parameters | 49B | Unknown |
| License | mit | mit |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Fireworks Ai (Standard), Together Ai (Standard) | DeepSeek (Standard), Deepinfra (Standard), Together Ai (Standard) |
| Capabilities | agents, chat, coding, generation, reasoning, tools | agents, chat, fim, generation, reasoning, responses, structured_outputs, tools, vision |
| Architecture design | Unknown | Causal Encoder-Decoder (20 encoder + 20 decoder layers) |
| Backbone parameters | Unknown | 552000000000 parameters |
| Active parameters during decode | Unknown | 16000000000 parameters |
| Active parameters during prefill | Unknown | 8000000000 parameters |
| Pre-training corpus | Unknown | 45000000000000 tokens |
| Reasoning effort range | Unknown | 1–100 |
| Routed experts per MoE layer | Unknown | 384 experts |
| Routed experts per token | Unknown | 6 experts |
| Transformer layers | Unknown | 40 layers |
DeepSeek V4 Pro 0813 Capabilities
DeepSeek V4.1 Flash Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
DeepSeek-V4-FlashDeepSeek | vs | DeepSeek-V4-Pro-0813DeepSeek | family variantstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | DeepSeek-V4-Pro-0813DeepSeek | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs | Grok 4.6xAI | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | DeepSeek-V4-Pro-0813DeepSeek | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  GLM-5.3Z.ai | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | DeepSeek-V4-Pro-0813DeepSeek | cross-developer peerstext |
DeepSeek-V4-Pro-0813DeepSeek | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
DeepSeek V4 Pro 0813 vs DeepSeek V4.1 Flash FAQs
Is DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both DeepSeek V4 Pro 0813 and DeepSeek V4.1 Flash, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
DeepSeek V4 Pro 0813 is $1.30 and DeepSeek V4.1 Flash is $0.15 per million tokens, so DeepSeek V4.1 Flash is cheaper on this metric. DeepSeek V4 Pro 0813 is $2.60 and DeepSeek V4.1 Flash is $0.60 per million tokens, so DeepSeek V4.1 Flash is cheaper on this metric.
Which has a larger context window, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
Neither model has a larger sourced context window in this comparison. DeepSeek V4 Pro 0813 is 1,049K and DeepSeek V4.1 Flash is 1,049K.
Which performs better in benchmarks, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.
Can DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash be self-hosted?+
Both models have the same recorded self-hosting status: supported. DeepSeek V4 Pro 0813 is open weight; DeepSeek V4.1 Flash is open weight.
Can DeepSeek V4 Pro 0813 and DeepSeek V4.1 Flash understand images?+
DeepSeek V4 Pro 0813 is not documented with image input; DeepSeek V4.1 Flash is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
Neither has a larger sourced maximum output. DeepSeek V4 Pro 0813 is — and DeepSeek V4.1 Flash is 393K.
Do DeepSeek V4 Pro 0813 and DeepSeek V4.1 Flash support reasoning and tool use?+
DeepSeek V4 Pro 0813: reasoning and tool calling. DeepSeek V4.1 Flash: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
DeepSeek V4 Pro 0813 has 3 sourced provider routes; DeepSeek V4.1 Flash has 3, a tie.
Which offers better value, DeepSeek V4 Pro 0813 or DeepSeek V4.1 Flash?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.