Budget GLM lane for fast coding help, routing, and everyday automation
Specification
zhipuai listing
Context
200K
Max output
131K
Released
2026-01-19
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · zhipuai list price
Input
free
Output
free
Cache read
free
Cache write
free
Rate limits
as listed
Requests per minute
300
Quality
3 benchmarks · 1 source
Composite
43rd
percentile of 334 scored models
Rank
192 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning34th2/4 bench
math64th1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3 ±6.6 | default | Epoch AI | 2026-08-30 |
| GPQA diamond | 60.5 ±2.9 | default | Epoch AI | 2026-08-30 |
| Chess Puzzles | 0.0 ±0.0 | default | Epoch AI | 2026-08-28 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 26 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| zhipuaivendor | free | free | free | free | 200K | 131K | — |
| empiriolabs | free | free | — | — | 200K | 131K | — |
| huggingface · zai-org | free | free | — | — | 200K | 128K | — |
| kenari · free | free | free | — | — | 200K | 131K | — |
| pendra | free | free | — | — | 200K | 131K | — |
| zai | free | free | free | free | 200K | 131K | — |
| zai · zai | free | free | free | free | 200K | 128K | — |
| deepinfra | $0.06 | $0.40 | $0.01 | — | 203K | — | — |
| deepinfra · zai-org | $0.06 | $0.40 | $0.01 | — | 203K | 16K | — |
| llmgateway | $0.06 | $0.40 | $0.01 | free | 200K | 131K | — |
| llmgateway-providers · embercloud | $0.06 | $0.40 | $0.01 | — | 200K | 131K | — |
| openrouter | $0.06 | $0.40 | $0.01 | free | 200K | 32K | — |
| cloudflare | $0.0605 | $0.40 | — | — | 131K | 131K | — |
| cloudflare-workers-ai · cf | $0.0605 | $0.40 | — | — | 131K | 131K | — |
| edenai | $0.0605 $0.06 | $0.40 | $0.01 | — | 131K 203K | 131K | — |
| kilo · z-ai | $0.0605 | $0.40 | — | — | 131K | 118K | — |
| openrouter · z-ai | $0.0605 | $0.40 | — | — | 200K | 118K | — |
| jiekou · zai-org | $0.07 | $0.40 | — | — | 200K | 128K | — |
| merge-gateway · zai | $0.07 | $0.40 | — | — | 200K | 128K | — |
| nano-gpt · thinking | $0.07 | $0.40 | $0.035 | — | 200K | 128K | — |
| nano-gpt · z-ai | $0.07 | $0.40 | $0.035 | — | 200K | 128K | — |
| novita | $0.07 | $0.40 | $0.01 | — | 200K | 128K | — |
| novita-ai · zai-org | $0.07 | $0.40 | $0.01 | — | 200K | 128K | — |
| vercel · zai | $0.07 | $0.40 | — | — | 200K | 131K | — |
| cortecs | $0.08 | $0.478 | — | — | 203K | 203K | — |
| poe | — | — | — | — | 200K | 66K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | openrouter | Cache read | free |
| 2026-09-06 | openrouter | Cache read | $0.01 |
| 2026-09-02 | edenai | Input | $0.06 |
| 2026-09-04 | edenai | Input | $0.0605 |
| 2026-09-02 | kilo · z-ai | Input | $0.06 |
| 2026-09-08 | kilo · z-ai | Input | $0.0605 |
| 2026-09-02 | openrouter | Input | $0.07 |
| 2026-09-06 | openrouter | Input | $0.06 |
| 2026-09-02 | openrouter · z-ai | Input | $0.06 |
| 2026-09-08 | openrouter · z-ai | Input | $0.0605 |
More from Zhipu
most-hosted first