ligero abierto MoE modelo diseñado para efficient en-device o workstation servicio con bajo hardware overhead.
Technical Specifications
- Provider
- Zhipu AI
- Category
- open-source
- Release Date
- 2025-07
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- glm-4-5-air
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2027+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 19 GB VRAM (4-bit Quantized) · 65 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
GLM-4.5-Air Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to GLM-4.5-Air:
Benchmark Scores & 6-Axis Capability Radar
- GPQA Diamond
- 52%
- MMLU-Pro
- 70%
- HumanEval
- 81%
- Chatbot Arena Elo
- 1255pts
Strengths
- bajo hardware huella se ejecuta comfortably en dual RTX 3090/4090 workstations
- rápido inferencia rendimiento exceeding 120 tokens/sec
- bueno instrucción alignment para day-un-day corporativo tareas
Limitations & Trade-offs
- menor precisión en complejo algorithmic matemáticas y formal proofs
- carece de nativo visual comprensión
Editorial Assessment
un economical abierto MoE caballo de batalla proporcionando alto rendimiento en modest hardware.
Best for: desarrollador desktop assistance, cliente soporte bots, y internal documento búsqueda
Compare GLM-4.5-Air
Frequently Asked Questions about GLM-4.5-Air
How much does the GLM-4.5-Air API cost per 1M tokens?+
GLM-4.5-Air by Zhipu AI is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the GLM-4.5-Air pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in GLM-4.5-Air's context window?+
GLM-4.5-Air features a 131K tokens context window, which equals approximately 98,304 English words or ~262 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.
Can I run GLM-4.5-Air locally on my own GPU (Open Weights)?+
Yes, GLM-4.5-Air (30B MoE) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Zhipu AI train on data sent to the GLM-4.5-Air API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does GLM-4.5-Air perform on coding and reasoning benchmarks?+
GLM-4.5-Air achieves a composite Intelligence Index of 74/100, scoring N/A% on SWE-bench Verified, 52% on GPQA Diamond, 70% on MMLU-Pro, and 1255 pts on Chatbot Arena Elo.
What is GLM-4.5-Air best used for?+
GLM-4.5-Air is best suited for: desarrollador desktop assistance, cliente soporte bots, y internal documento búsqueda. Assessment: un economical abierto MoE caballo de batalla proporcionando alto rendimiento en modest hardware.
Zhipu AI Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Zhipu AI's flagship reasoning tier:
GLM-5.2
GLM-5.1
GLM-5V-Turbo
GLM-5-Turbo
GLM-5
GLM-4.7-FlashX
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to GLM-4.5-Air:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
Un modelo de IA entrenado para invertir cómputo adicional en pensar y validar hipótesis lógicas antes de responder, diseñado para problemas complejos de ingeniería y matemáticas.
Una técnica de razonamiento paso a paso donde el modelo genera pensamientos intermedios antes de formular la respuesta final, mejorando radicalmente la resolución de problemas matemáticos y lógicos.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.
Fuentes: Zhipu AI Hugging Face Repository↗