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. | 8B/43B | 106B |
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. | 4k | 128k |
| 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. | — | $0.20 |
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. | — | $1.10 |
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. | — | $0.03 |
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. | — | $0.13Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.85Novita |
| — | $68.50Novita · bf16 | |
| These models have no shared benchmark scores. | ||
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% |
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. | — | 70.7% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 10.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 98.1% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 89.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 75% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 81.4% |
| Overview | ||
| Company | NVIDIA | Z.ai |
| Release date | Mar 21 2023 | Jul 28 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
NeMo GPT (8B/43B)vsClaude Fable 5.2GLM-4.5-AirvsClaude Fable 5.2NeMo GPT (8B/43B)vsGPT-6.2 AstraGLM-4.5-AirvsGPT-6.2 AstraNeMo GPT (8B/43B)vsGemini 4 NeonGLM-4.5-AirvsGemini 4 NeonNeMo GPT (8B/43B)vsMuse EmberGLM-4.5-AirvsMuse EmberNeMo GPT (8B/43B)vsGrok 4.7GLM-4.5-AirvsGrok 4.7NeMo GPT (8B/43B)vsDeepSeek-V4.1-Flash-1017GLM-4.5-AirvsDeepSeek-V4.1-Flash-1017Frequently asked questions
NeMo GPT (8B/43B) and GLM-4.5-Air don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only GLM-4.5-Air has a verified first-party price for an available API: $0.20 per million input tokens and $1.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for NeMo GPT (8B/43B). NeMo GPT (8B/43B) shipped 860 days before GLM-4.5-Air, so benchmark comparisons should account for the intervening progress.
NeMo GPT (8B/43B) has 8B/43B parameters, while GLM-4.5-Air has 106B. Context windows are 4k (NeMo GPT (8B/43B)) vs 128k (GLM-4.5-Air). NeMo GPT (8B/43B) is closed, while GLM-4.5-Air is open weight.
Direct benchmark comparisons are unavailable — NeMo GPT (8B/43B) and GLM-4.5-Air don't publish scores on any of the same benchmarks.