Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 1.6T | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 400k |
| 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 | $1.75 |
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 | $14.00 |
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 | $0.175 |
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. | $0.0999Relace | $1.75Azure |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.98DeepSeek | $14.00Azure |
| $231DeepSeek list price | $1,050OpenAI list price | |
| Benchmarks | ||
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% | 24% |
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% | 85% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 56.8% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 68% |
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% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 77.3% |
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 · 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% | — |
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% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 64.7% |
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% | — |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 70.9% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | — | 1153 |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Aug 13 2026 | Feb 5 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Fable 5.2GPT-5.3-CodexvsClaude Fable 5.2DeepSeek-V4-Pro-0813vsGemini 4 CarbonGPT-5.3-CodexvsGemini 4 CarbonDeepSeek-V4-Pro-0813vsMuse EmberGPT-5.3-CodexvsMuse EmberDeepSeek-V4-Pro-0813vsGrok 4.7GPT-5.3-CodexvsGrok 4.7DeepSeek-V4-Pro-0813vsMistral Large 4GPT-5.3-CodexvsMistral Large 4DeepSeek-V4-Pro-0813vsKimi K3.1 ProGPT-5.3-CodexvsKimi K3.1 ProFrequently asked questions
DeepSeek-V4-Pro-0813 and GPT-5.3-Codex are evenly matched across the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). DeepSeek-V4-Pro-0813 is cheaper on both input and output: $0.66 vs $1.75 per million input tokens, and $1.98 vs $14.00 per million output tokens. Figures are base-tier rates. GPT-5.3-Codex shipped 189 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (DeepSeek-V4-Pro-0813) vs 400k (GPT-5.3-Codex). DeepSeek-V4-Pro-0813 is open weight, while GPT-5.3-Codex is closed.
On BullshitBench v2, DeepSeek-V4-Pro-0813 leads at 35% vs GPT-5.3-Codex at 24%. On SWE-Bench Verified, GPT-5.3-Codex leads at 85% vs DeepSeek-V4-Pro-0813 at 80.6%.