Z.AI
Model developerchat.z.ai ↗
Models on Z.AI · prices & measurements for models served by Z.AI’s APIUSD / MTOK · VERIFIED 25 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
| $0.15 | $0.50 | 1.05M | fp8 | 3.8s° | 43° tok/s | — | $0.032 elsewhere | |
| $0.20 | $1.10 | 131K | fp8 | ✕ | ✕ | — | $0.13 elsewhere | |
| $0.30 | $0.90 | 131K | fp8 | ✕ | ✕ | — | cheapest here | |
| $0.37 | $1.25 | 1.05M | fp8 | 2.2s° | 194° tok/s | — | only provider | |
| $0.60 | $2.20 | 203K | fp4 | 8.8s° | 3448° tok/s | 2/5 | $0.40 elsewhere | |
| $0.60 | $2.20 | 203K | fp4 | 8.4s° | 766° tok/s | 2/5 | $0.43 elsewhere | |
| $0.60 | $1.80 | 66K | fp8 | 4.6s° | 89° tok/s | — | cheapest here | |
| $0.60 | $2.20 | 131K | fp8 | 8.8s° | — | — | only provider | |
| $1.00 | $3.20 | 203K | fp8 | 4.2s° | — | — | $0.60 elsewhere | |
| $1.20 | $4.00 | 203K | fp8 | 4.1s° | 32° tok/s | — | only provider | |
| $1.20 | $4.00 | 203K | — | ✕ | ✕ | — | only provider | |
| $1.40 | $4.40 | 1.05M | fp8 | 2.7s° | 78° tok/s | — | $0.031 elsewhere | |
| $1.40 | $4.40 | 1.05M | fp8 | ✕ | ✕ | — | $0.07 elsewhere | |
| $1.40 | $4.40 | 203K | fp8 | 8.7s° | 2743° tok/s | — | $0.966 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Z.AI’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page
Not served on Z.AI’s own API
Older Z.AI models retired from the first-party API but still available through cloud platforms.