Inference provider

ModelRun: every model it hosts

2 endpoints tracked. Hosts may use different quantizations, context limits, and serving defaults, so compare price together with reliability and configuration. On this host family, the same model costs up to 7× more depending on which endpoint serves it.

Verified 2026-10-21 · source: OpenRouter public API

Cheapest here

MiniMax: MiniMax M3

$0.300 in / $1.30 out per 1M

Priciest here

Z.ai: GLM 5.3

$2.10 in / $6.60 out per 1M

Model	Input /1M	Output /1M	Cache read	Context	Uptime 1d	Throughput
MiniMax: MiniMax M3fp8	$0.300	$1.30	$0.050	1049K	99.7%	—
Z.ai: GLM 5.3fp4	$2.10	$6.60	$0.400	1049K	96.7%	—

Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.