modelbenchmark.io

GLM 4.7 Original

Zhipu · glm-4-7-original

Compare

GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).

Specification

most-agreed values

Context
200K
Max output
66K
Released
2025-12-22
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.4004
Output
$1.9292
Cache read
$0.0801

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · thinking$0.4004$1.9292$0.0801—200K66K—
nano-gpt · z-ai$0.4004$1.9292$0.0801—200K66K—

Price history

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

DateHostField$/M
2026-09-02nano-gpt · thinkingCache read$0.11
2026-10-27nano-gpt · thinkingCache read$0.0801
2026-09-02nano-gpt · z-aiCache read$0.11
2026-10-27nano-gpt · z-aiCache read$0.0801
2026-09-02nano-gpt · thinkingInput$0.60
2026-10-27nano-gpt · thinkingInput$0.4004
2026-09-02nano-gpt · z-aiInput$0.60
2026-10-27nano-gpt · z-aiInput$0.4004
2026-09-02nano-gpt · thinkingOutput$2.20
2026-10-27nano-gpt · thinkingOutput$1.9292
2026-09-02nano-gpt · z-aiOutput$2.20
2026-10-27nano-gpt · z-aiOutput$1.9292

More from Zhipu

most-hosted first