GLM 5
Z.ai · Open weights · Released Feb 11, 2026 · z-ai/glm-5
Best $0.60 in / $1.92 out via GMICloud · fp8 · 203K ctx at this price (headline 205K)
205K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 10 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.55 | $1.76 | — | — | — | ✕ | ✕ | — | — | |
| $0.60 | $1.92 | $0.12 | 203K | fp8 | 4.3s | 73 tok/s | 3/5 | 98.9% | |
| $0.60 | $1.92 | $0.12 | 198K | fp8 | 1.7s | 119 tok/s | 2/5 | 100.0% | |
| $0.70 | $2.24 | $0.14 | 203K | fp8 | ✕ | ✕ | 2/5 | 100.0% | |
| $0.87 | $2.78 | — | — | — | — | — | — | — | |
| $0.95 | $2.55 | $0.20 | 205K | fp8 | 3.1s | 108 tok/s | 2/5 | 99.4% | |
| $1.00 | $3.20 | $0.20 | 203K | fp8 | 4.2s | — | — | 100.0% | |
| $1.00 | $3.20 | — | 203K | — | ✕ | ✕ | — | 99.3% | |
| $1.00 | $3.20 | $0.20 | 203K | fp8 | ✕ | ✕ | — | 100.0% | |
| $1.00 | $3.20 | $0.20 | 198K | fp8 | 0.91s | 111 tok/s | — | 98.3% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.60 / $1.92
per MTok in / out
CACHE READ $0.12
Recent changesRSS ↗
Sep 23, 2026endpoint added · cheaperinference8 → 10
Sep 10, 2026endpoint removed · deepinfra9 → 8
Sep 9, 2026endpoint removed · digitalocean10 → 9
Sep 3, 2026endpoint removed · atlascloud11 → 10
About
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
Specifications
Context window204,800
Max output128,000
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedFeb 11, 2026
TokenizerOther
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/z-ai/glm-5)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks18 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.