Compare AI models
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.22 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.66 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.007 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.25DeepInfra | $0.016Relace |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $0.95DeepInfra | $0.18DeepInfra |
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 66% | 79% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 15.9% | 34.8% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 39% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 74.8% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 82.7% |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | — | 70.3% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 73.2% |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 76.7% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 61.4% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 25.1% |
| Overview | ||
| Company | DeepSeek | DeepSeek |
| Release date | Aug 21 2025 | Jul 31 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1vsClaude Haiku 5.5DeepSeek-V4-Flash-0731vsClaude Haiku 5.5DeepSeek V3.1vsGPT-6.1 SolDeepSeek-V4-Flash-0731vsGPT-6.1 SolDeepSeek V3.1vsGemini 4 ArgonDeepSeek-V4-Flash-0731vsGemini 4 ArgonDeepSeek V3.1vsMuse Spark 1.3DeepSeek-V4-Flash-0731vsMuse Spark 1.3DeepSeek V3.1vsGrok 4.7DeepSeek-V4-Flash-0731vsGrok 4.7DeepSeek V3.1vsMistral Large 4DeepSeek-V4-Flash-0731vsMistral Large 4Frequently asked questions
DeepSeek-V4-Flash-0731 leads DeepSeek V3.1 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam). Only DeepSeek-V4-Flash-0731 has a verified first-party API price: $0.22 per million input tokens and $0.66 per million output tokens. No pay-as-you-go API rate is tracked for DeepSeek V3.1. DeepSeek V3.1 shipped 344 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs DeepSeek V3.1 at 66%. On Humanity's Last Exam · with tools, DeepSeek-V4-Flash-0731 leads at 34.8% vs DeepSeek V3.1 at 15.9%.