Z.ai

GLM 4.5 Air

131K ctxText Tools Reasoning

Released Jul 28, 2025 · 61B tokens this week · 3 providers

Overview

The lightweight member of the GLM 4.5 family, tuned for fast agentic use on modest hardware. Keeps tool calling and light reasoning while cutting cost substantially. A sensible sub-agent model inside a larger pipeline.

agentsprogrammingroleplay

Providers

Reference data — not yet measured from live traffic

PROVIDERMAX OUTOUTPUT /MQUANT
Novita AICheapest
131K33K$0.14$0.86520ms10598.50%fp8
DeepInfra
131K33K$0.15$0.93500ms11298.60%fp8
Together AI
131K33K$0.16$0.99195ms14099.30%Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

GLM 4.5 Air$0.68
GPT-5.2$10.94

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.5-air",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'