modelbenchmark.io

Standard Compute

standardcompute

Compare

Flat-rate smart-routing gateway: one model id, each request routed across the customer's enabled models from a curated ~1M-context catalog (Claude, GPT, Gemini, DeepSeek, GLM, Qwen, Kimi, MiniMax, Grok, MiMo) or pinned to a user-selected model

Specification

most-agreed values

Context
1M
Max output
50K
Released
2026-03-01
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, pdf
Output
text

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
standardcompute————1M50K—