GLM-5.1 (TEE)
Z.ai
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
- Tool calling: yes
- Image input: no
Released
Apr 2026Modalities
Text · Tool callingBest price on SayGM
-58.8%In
Cached
Out
per Mtok*
SayGM vs. list price
SayGM's best available rate for glm-5.1-tee next to the published list price — 58.8% off.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.5768per Mtok | $1.40 |
| Output | $1.8128per Mtok | $4.40 |
| Cache read | $0.20188per Mtok | $0.49 |
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$1.13
$1.40Cached input
$0.43
$0.49Output
$4.08
$4.40How the effective price is calculated
Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 2 windows: 145 requests and 2,065,537 input-side tokens. Most recent window closed 2026-08-26 14:17 UTC.
Who's serving this model
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 58.8% off | $0.58 | $1.81 |
| Provider 2 | 4.2% off | $1.34 | $4.21 |
| Provider 3 | — | $1.40 | $4.40 |
Performance
Measured on the requests SayGM routed to this model.
- Throughput
- 42.7 tok/sover 235 requests
- Time to first token
- 4.8 sover 235 requests
- Request success rate
- 100.0% over 112 requests
Benchmarks
Fixed-seed suites SayGM runs against this model.
Frequently asked questions
How much does glm-5.1-tee cost on SayGM?
The best available rate for glm-5.1-tee on SayGM right now is $0.58 per million input tokens and $1.81 per million output tokens.
How much cheaper is SayGM than list price?
SayGM's best available rate for glm-5.1-tee is 58.8% off list price.
Is glm-5.1-tee OpenAI-compatible on SayGM?
Yes. glm-5.1-tee is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.