Friendli
Models on Friendli · prices & measurements for models served by Friendli’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|
 Gemma 4 31BGoogle | $0.14 | $0.40 | 262K | — | ✕ | ✕ | $0.09 elsewhere |
 GLM 5.3 FlashZ.ai | $0.15 | $0.50 | 1.05M | — | 0.95s° | 146° tok/s | $0.032 elsewhere |
 MiniMax M2.5MiniMax | $0.30 | $1.20 | 197K | — | 0.3s° | 197° tok/s | $0.27 elsewhere |
 DeepSeek V3.2DeepSeek | $0.50 | $1.50 | 164K | — | 1.9s° | 40° tok/s | $0.209 elsewhere |
| GLM 5.3Z.ai | $1.26 | $3.96 | 1.05M | — | 0.87s° | 133° tok/s | $0.039 elsewhere |
| GLM 5.2Z.ai | $1.40 | $4.40 | 1.05M | — | ✕ | ✕ | $0.03 elsewhere |
| GLM 5.1Z.ai | $1.40 | $4.40 | 203K | — | ✕ | ✕ | $0.966 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Friendli’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page