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. | $0.66 | — |
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. | $1.98 | — |
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. | $0.022 | — |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.1233Relace | $0.15DeepSeek |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.40Baidu | $0.60DeepSeek |
| $46.66Baidu · fp8 | $60.00DeepSeek | |
| Benchmarks | ||
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 42.7% | 42.6% |
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. | 31.8% | 60.5% |
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. | 35% | — |
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. | 80.6% | — |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 77% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 68.2% |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | — | 42.3% |
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. | 87.9% | — |
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. | 74.1% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.3% | — |
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. | 60% | — |
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. | 61.3% | — |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 35.4% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 83% |
| Overview | ||
| Company | DeepSeek | DeepSeek |
| Release date | Aug 13 2026 | Oct 17 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Haiku 5.5DeepSeek-V4.1-Flash-1017vsClaude Haiku 5.5DeepSeek-V4-Pro-0813vsGPT-6.1 SolDeepSeek-V4.1-Flash-1017vsGPT-6.1 SolDeepSeek-V4-Pro-0813vsGemini 4 ArgonDeepSeek-V4.1-Flash-1017vsGemini 4 ArgonDeepSeek-V4-Pro-0813vsMuse Spark OpenDeepSeek-V4.1-Flash-1017vsMuse Spark OpenDeepSeek-V4-Pro-0813vsGrok 4.7DeepSeek-V4.1-Flash-1017vsGrok 4.7DeepSeek-V4-Pro-0813vsMistral Large 4DeepSeek-V4.1-Flash-1017vsMistral Large 4Frequently asked questions
DeepSeek-V4-Pro-0813 and DeepSeek-V4.1-Flash-1017 are evenly matched across the 2 benchmarks they both report (Humanity's Last Exam, AutomationBench). Only DeepSeek-V4-Pro-0813 has a verified first-party API price: $0.66 per million input tokens and $1.98 per million output tokens. No pay-as-you-go API rate is tracked for DeepSeek-V4.1-Flash-1017. DeepSeek-V4-Pro-0813 shipped 65 days before DeepSeek-V4.1-Flash-1017, 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 Humanity's Last Exam · no tools, DeepSeek-V4-Pro-0813 leads at 42.7% vs DeepSeek-V4.1-Flash-1017 at 42.6%. On AutomationBench, DeepSeek-V4.1-Flash-1017 leads at 60.5% vs DeepSeek-V4-Pro-0813 at 31.8%.