GLM-4.5 Air

Zhipu AI's lightweight GLM-4.5 variant for cost-effective tasks.

Input price: $0.12848
Output price: $0.3212
Context: 131K
Max output: 98K
Modalities: InputTextOutputText
Capability: —
Human preference: 1384
30-day uptime: —
Released: 2025-08-13
Knowledge cutoff: 2025-04

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

AutoInput$0.12848Output$0.3212Cache read$0.025696Context131KMax output98KWe send each request to the best-priced healthy provider. You pay that provider’s price.Zhipu AI (ChatGLM)Input$0.12848Output$0.3212Cache read$0.025696Max output96KChinafp8No training

Pricing

All prices for this model, by service tier.

Prompt ≤ 32K tokens

Input: $0.12848; per 1M tokens
Output: $0.9636; per 1M tokens
Cache read: $0.025696; per 1M tokens

Prompt > 32K tokens

Input: $0.19272; per 1M tokens
Output: $1.2848; per 1M tokens
Cache read: $0.038544; per 1M tokens

Make a request

Set your provider preferences, then copy the request. It reads your API key from OHMYGPT_API_KEY.

Keep conversations on one provider

Later turns reuse the provider’s prompt cache, which can lower cost and latency.

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.5-air",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Similar models

Other models with the same output types at a similar price.

Better value: more capable, lower price
Pareto frontier
Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GLM-4.5 AirThis model

Capability: —
Input: $0.12848
Output: $0.3212

Gemma 3 27B Instruct

Capability: —
Input: $0.132
Output: $0.22

GPT-4o-mini

Capability: 126
Input: $0.135
Output: $0.54

Doubao Seed 2.1 Lite (260915)

Capability: —
Input: $0.1168
Output: $0.3942

Tencent Hy3

Capability: —
Input: $0.146
Output: $0.584

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text