The Known Good Updated 29 Jul 2026
Providers· First-party endpoint· 11 tracked models

Z.AI — pricing & performance

Compare models All providers Data sources
Models served
11
of 947 tracked models
Mean output speed
32
tokens per second, averaged over
11 measured endpoints
Mean latency
5.5s
time to first token, averaged over
11 measured endpoints
Cheapest blended
$0.42
per 1M tokens at a 3:1
input:output blend
Output speed on Z.AI

Median output tokens per second for all 11 models on Z.AI with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.

⇩
50
50
42
34
34
32
31
30
22
21
11
The Known Good
11 models on Z.AI
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Z.ai: GLM 4.5 Z.ai $0.60 $2.20 $1.00 34 11.1s 131k
Z.ai: GLM 4.5 Air Z.ai $0.20 $1.10 $0.42 30 2.0s 131k
Z.ai: GLM 4.5V Z.ai $0.60 $1.80 $0.90 50 5.7s 66k
Z.ai: GLM 4.6 Z.ai $0.60 $2.20 $1.00 34 3.6s 203k
Z.ai: GLM 4.6V Z.ai $0.30 $0.90 $0.45 11 2.0s 131k
Z.ai: GLM 4.7 Z.ai $0.60 $2.20 $1.00 21 9.5s 203k
Z.ai: GLM 5 Z.ai $1.00 $3.20 $1.55 31 7.3s 203k
Z.ai: GLM 5 Turbo Z.ai $1.20 $4.00 $1.90 22 5.5s 203k
Z.ai: GLM 5.1 Z.ai $1.40 $4.40 $2.15 42 6.5s 203k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 32 4.2s 1.05M
Z.ai: GLM 5V Turbo Z.ai $1.20 $4.00 $1.90 50 3.4s 203k
The Known Good
Source. Prices, endpoint availability and throughput for Z.AI are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.