glm-5.2
GLM-5.2 · Z.ai
×1.0
serving
- Multiplier
- ×1.0 (reference)
- Context served
- 128K tokens
- Max output
- 8.19K tokens
- Parameters
- not published
- Throughput
- not yet measured
- License
- MIT
in ×1.0 · cached ×0.185714 · out ×3.142857added Jul 23, 2026
An OpenAI-compatible endpoint for open-weight models, served through named providers. The weighting formula is public, every response carries the arithmetic behind its own charge, and every limit is published before you pay for it.
The endpoint speaks the OpenAI chat-completions API, so anything that takes a base URL and a key already works. This is the configuration, not a simplified version of it.
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"tium": {
"npm": "@ai-sdk/openai-compatible",
"name": "Tium",
"options": {
"baseURL": "https://api.tium.ai/v1"
},
"models": {
"glm-5.2": {
"name": "GLM-5.2",
"limit": {
"context": 128000,
"output": 32768
}
}
}
}
}
}Models are content here, not a hardcoded page. The catalog carries the next model without a redesign, and it can say when one is retired.
GLM-5.2 · Z.ai
Every performance figure on a model card carries the date it was measured, and the ones that have not been measured say so. The full catalog, with each model’s multiplier and published weights, is on /models.
Three things make the claim checkable rather than rhetorical.
How a request turns into a charge is written down and published, not folded into a headline price. If the weighting changes, it changes in public and only for requests made after it.
Every response carries what it cost, what remains, and what the concurrency limit is. You do not have to take the number on this page on trust.
Each model says who serves it. Where that is a third-party provider, the model card says so plainly rather than implying capacity Tium does not own.
X-Tium-Request-Id: req_8f2c1a94e7
X-Tium-Tokens-In: 12400
X-Tium-Tokens-Cached: 3180
X-Tium-Tokens-Out: 8920
X-Tium-Weighted-Tokens: 48875
X-Tium-Model-Multiplier: 1.0
X-Tium-Balance-Remaining: 1243908
X-Tium-Concurrency-Limit: 8
X-Tium-Concurrency-Remaining: 5Input and output tokens have very different costs to serve. Counting them as one number either overcharges long-context work or undercharges generation loops, so they are weighted, and the weights are published rather than folded into a price.
WT = (in × W_IN + cached × W_CACHED + out × W_OUT) × M_model
W_IN = 1.0 # definitional anchor: one input token on glm-5.2
W_CACHED = 0.1857 # what a cache hit costs against a miss
W_OUT = 3.1429 # the provider's output ÷ input price ratio
M_model = 1.0 # glm-5.2 is the reference; others convert to itEvery request you make will show this arithmetic for itself: the token counts, the weights applied, and the multiplier, adding up to the number you were charged.
Tiers are a monthly allotment of weighted tokens, a published concurrency limit, and a published overage rate. The figures follow from what these models cost to serve rather than being chosen, and every one of them is on the pricing page.
Every tier, allotment, concurrency limit and overage rate is on /pricing.