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. | 671B | 30B |
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. | 128k | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.00 |
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. | — | $0.00 |
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. | — | $0.00 |
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. | $0.50DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.15DeepInfra | — |
| $208DeepInfra · fp4 | $0.00Z.ai list price | |
| 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. | 57.6% | 59.2% |
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. | 73.3% | 64% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 87.5% | 91.6% |
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. | 8% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 42.8% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 17.7% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 91.4% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 81% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 27.8% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85% | — |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | May 28 2025 | Jan 19 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528vsClaude Fable 5.2GLM-4.7-FlashvsClaude Fable 5.2DeepSeek R1-0528vsGPT-6.2 AstraGLM-4.7-FlashvsGPT-6.2 AstraDeepSeek R1-0528vsGemini 4 HydrogenGLM-4.7-FlashvsGemini 4 HydrogenDeepSeek R1-0528vsMuse EmberGLM-4.7-FlashvsMuse EmberDeepSeek R1-0528vsGrok 4.7GLM-4.7-FlashvsGrok 4.7DeepSeek R1-0528vsMistral Large 4GLM-4.7-FlashvsMistral Large 4Frequently asked questions
GLM-4.7-Flash leads DeepSeek R1-0528 on 2 of the 3 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, AIME 2025). Only GLM-4.7-Flash has a verified first-party price for an available API: $0.00 per million input tokens and $0.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek R1-0528. DeepSeek R1-0528 shipped 236 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 has 671B parameters, while GLM-4.7-Flash has 30B. Context windows are 128k (DeepSeek R1-0528) vs 200k (GLM-4.7-Flash).
On SWE-Bench Verified, GLM-4.7-Flash leads at 59.2% vs DeepSeek R1-0528 at 57.6%. On LiveCodeBench, DeepSeek R1-0528 leads at 73.3% vs GLM-4.7-Flash at 64%. On AIME 2025, GLM-4.7-Flash leads at 91.6% vs DeepSeek R1-0528 at 87.5%.