BaseTen
Models on BaseTen · prices & measurements for models served by BaseTen’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 gpt-oss-120bOpenAI | $0.10 | $0.50 | 128K | fp4 | 0.26s° | 240° tok/s | — | $0.03 elsewhere |
 DeepSeek V4 Flash 0731DeepSeek | $0.13 | $0.26 | 1.05M | fp8 | 0.38s° | 265° tok/s | — | $0.01 elsewhere |
 GLM 5.3 FlashZ.ai | $0.15 | $0.50 | 1.05M | fp8 | ✕ | ✕ | — | $0.032 elsewhere |
| DeepSeek V4.1 FlashDeepSeek | $0.30 | $1.20 | 1.05M | fp8 | 2s° | 166° tok/s | — | $0.018 elsewhere |
 Nemotron 3 UltraNVIDIA | $0.60 | $2.40 | 203K | fp4 | 0.51s° | 341° tok/s | — | $0.50 elsewhere |
| GLM 5.3Z.ai | $1.40 | $4.40 | 1.05M | fp4 | 1.1s° | 86° tok/s | — | $0.039 elsewhere |
| GLM 5.2Z.ai | $1.40 | $4.40 | 1.05M | fp8 | 1.8s° | 138° tok/s | — | $0.03 elsewhere |
 Kimi K3Moonshot AI | $3.00 | $15.00 | 1.05M | fp8 | ✕ | ✕ | 1/5 | $0.68 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for BaseTen’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page