modelbenchmark.io

Claw High

claw-high

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-05-11
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.60
Output
$1.10
Cache read
$0.20

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.60$1.10$0.20—1M131K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02nano-gptCache read$0.20
2026-10-09nano-gptCache read$0.13
2026-10-10nano-gptCache read$0.20
2026-09-02nano-gptInput$1.00
2026-10-09nano-gptInput$0.70
2026-10-10nano-gptInput$0.60
2026-09-02nano-gptOutput$3.20
2026-10-09nano-gptOutput$2.20
2026-10-12nano-gptOutput$1.10