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. | 4B | 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. | 128k | 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 | |
| Benchmarks | ||
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 96.2% | 98.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 55.1% | 75% |
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% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 75.5% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 10.6% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 89.4% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 46.3% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 81.4% |
| Overview | ||
| Company | NVIDIA | Z.ai |
| Release date | May 20 2025 | Jul 28 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2GLM-4.5-AirvsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsGPT-6.2 AstraGLM-4.5-AirvsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGemini 4 NeonGLM-4.5-AirvsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsMuse EmberGLM-4.5-AirvsMuse EmberLlama Nemotron Nano 4B v1.1vsGrok 4.7GLM-4.5-AirvsGrok 4.7Llama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017GLM-4.5-AirvsDeepSeek-V4.1-Flash-1017Frequently asked questions
GLM-4.5-Air leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (MATH-500, GPQA Diamond). 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 Llama Nemotron Nano 4B v1.1. Llama Nemotron Nano 4B v1.1 shipped 69 days before GLM-4.5-Air, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Nano 4B v1.1 has 4B parameters, while GLM-4.5-Air has 106B. Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 128k (GLM-4.5-Air).
On MATH-500, GLM-4.5-Air leads at 98.1% vs Llama Nemotron Nano 4B v1.1 at 96.2%. On GPQA Diamond, GLM-4.5-Air leads at 75% vs Llama Nemotron Nano 4B v1.1 at 55.1%.