Context
131K
Max output
128K
Serving providers
6
Cheapest input
$0.125 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
75 t/s
tokens / second
Time to first token
2.39s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 0% | default | — | |
| EvalComputeProxyFrozen Aug 18, 2026 | 122.9 | default | — | |
| GPQA Diamond | 73% | default | — | |
| Humanity's Last Exam | 7% | default | — | |
| IFBench | 38% | default | — | |
| LiveCodeBench | 68% | default | — | |
| Long-Context Reasoning | 47% | default | — | |
| MMLU-ProFrozen Aug 18, 2026 | 81% | default | — | |
| Omniscience | -61.5 | default | — | |
| Omniscience Accuracy | 0.2 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 31% | — | — | |
| TerminalBench Hard | 20% | default | — | |
| τ²-bench | 46% | default | — |
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.125 to $0.22 per 1M tokens across 6 providers, so the dearest route costs 76% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PinstripesCheapest | $0.125 | $0.45 | 1 | |||||||||||||
Standardpinstripes/ps/glm-4.5-air
| ||||||||||||||||
| Novita | $0.13 | $0.85 | 1 | |||||||||||||
Standardnovita/zai-org/glm-4.5-air
| ||||||||||||||||
| OpenRouter | $0.13 | $0.85 | 1 | |||||||||||||
Standardz-ai/glm-4.5-air
| ||||||||||||||||
| VercelVercel reseller quote | $0.20 | $1.10 | 1 | |||||||||||||
Standardzai/glm-4.5-air
| ||||||||||||||||
| Zai | $0.20 | $1.10 | 1 | |||||||||||||
Standardzai/glm-4.5-air
| ||||||||||||||||
| Fireworks AI | $0.22 | $0.88 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/glm-4p5-air
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 38% since first tracked
Cost calculator
estimate your monthly spend on this model$61
estimated / month
Model IDs
copy the exact identifier for your platformpinstripes/ps/glm-4.5-airz-ai/glm-4.5-airnovita/zai-org/glm-4.5-airzai/glm-4.5-airzai/glm-4.5-airfireworks_ai/accounts/fireworks/models/glm-4p5-air
Frequently asked questions
GLM 4.5 Air pricing, context and availabilityHow much does GLM 4.5 Air cost?
GLM 4.5 Air costs $0.125 per 1M input tokens from Pinstripes, and $0.45 per 1M output tokens from Pinstripes. Across 6 serving providers, input prices range from $0.125 to $0.22 per 1M tokens.
What is the context window of GLM 4.5 Air?
GLM 4.5 Air accepts up to 131K tokens of context and can return up to 128K output tokens.
Which providers serve GLM 4.5 Air?
GLM 4.5 Air is available from 6 serving providers, each with its own pricing and model ID. Pinstripes is currently the cheapest.
What can GLM 4.5 Air do?
GLM 4.5 Air supports tool use, reasoning, prompt caching and structured output.
Other Zhipu models
compare pricing across the Zhipu lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI