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. | $0.27SiliconFlow | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | — |
| $104SiliconFlow · fp8 | $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. | 68.4% | 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. | 74.9% | 64% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 38.5% | 42.8% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 88.4% | 91.6% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 57.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.7% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85% | — |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Sep 22 2025 | Jan 19 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Fable 5.2GLM-4.7-FlashvsClaude Fable 5.2DeepSeek V3.1 TerminusvsGPT-6.2 AstraGLM-4.7-FlashvsGPT-6.2 AstraDeepSeek V3.1 TerminusvsGemini 4 HydrogenGLM-4.7-FlashvsGemini 4 HydrogenDeepSeek V3.1 TerminusvsMuse EmberGLM-4.7-FlashvsMuse EmberDeepSeek V3.1 TerminusvsGrok 4.7GLM-4.7-FlashvsGrok 4.7DeepSeek V3.1 TerminusvsMistral Large 4GLM-4.7-FlashvsMistral Large 4Frequently asked questions
DeepSeek V3.1 Terminus and GLM-4.7-Flash are evenly matched across the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, BrowseComp, 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 V3.1 Terminus. DeepSeek V3.1 Terminus shipped 119 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek V3.1 Terminus has 671B parameters, while GLM-4.7-Flash has 30B. Context windows are 128k (DeepSeek V3.1 Terminus) vs 200k (GLM-4.7-Flash).
On SWE-Bench Verified, DeepSeek V3.1 Terminus leads at 68.4% vs GLM-4.7-Flash at 59.2%. On LiveCodeBench, DeepSeek V3.1 Terminus leads at 74.9% vs GLM-4.7-Flash at 64%. On BrowseComp, GLM-4.7-Flash leads at 42.8% vs DeepSeek V3.1 Terminus at 38.5%. On AIME 2025, GLM-4.7-Flash leads at 91.6% vs DeepSeek V3.1 Terminus at 88.4%.