Model
GLM-5.3 Flash (Zhipu/Z.ai)
Fast access (US)US Controlled · 0/100Call GLM-5.3 Flash (Zhipu/Z.ai) through Frontière AI's OpenAI-compatible API — fast access via a US provider, not EU sovereign: licence, per-token price.
About this model
GLM-5.3-Flash is a Mixture-of-Experts model from Z.ai, published on Hugging Face in August 2026 under the MIT license, and the first natively multimodal model in the GLM-5 series: it reads text, images and video and writes text. It has 320B total parameters with 18B active, on a newly trained base that mixes sparse and linear attention, which Z.ai says sharply reduces long-context serving costs; its configuration allows 1,048,576 tokens of context. Z.ai reports that it outperforms GLM-5.2 across benchmarks, with 84.3 on Terminal-Bench 2.1. Reasoning effort accepts low, high or max. Compared with GLM-5.3 in this catalogue, it is smaller, multimodal and MIT-licensed.
Sources, checked on 23 September 2026: huggingface.co/zai-org/GLM-5.3-Flash ↗ · z.ai/blog/glm-5.3-flash ↗
Specifications
- API model id
- glm-5.3-flash
- Availability
- Live
- Hosting jurisdiction
- Fast access (US)
- Served via
- Modal
- Publisher
- Zhipu / Z.ai
- Parameters
- 320B (18B active)
- Licence
- MIT
- Context window
- 1M
- Modality
- Multimodal (text + image)
Reasoning model — thinks before answering. Omit max_tokens or allow at least ~1,000.
Open weights & AI Act facts
Factual characteristics of this model's weights — stated, not certified. Under the EU AI Act, whether a deployment is compliant depends on the model, your role and your use case.
- Open weights
- Weights public and freely executable
- AI Act class
- GPAI — general-purpose AI
- Systemic risk
- Not assessed by us — training compute not published, or too close to the 10²⁵ FLOP threshold to call
- Data retention
- None at Frontière AI; provider-side retention follows Modal's own policy (not verified by us)
Compliance evidence
Provider facts for this model's serving path, as documented by Frontière AI; the retention row quotes each provider's own documentation where it exists. Dates reflect the most recent documented audit of each fact.
Last verified: 2026-09-11
- Provider / operator
- Modal (US company)
- Country
- United States
- Ownership / control
- US-controlled — CLOUD Act applies even in EU regions
- Jurisdiction
- US (default serving region observed outside the EU)
- Deployment
- Managed serverless (third party)
- Data retention
- None at Frontière AI; provider-side retention follows Modal's own policy (not verified by us)
- Fallback route
- OpenRouter (US company, New York) — None at Frontière AI; provider-side retention follows the policy of whichever provider OpenRouter picks (not verified by us)
Frontière AI retains neither prompts nor completions from API calls; processing is structured to fit a short DPA (Art. 28 GDPR). DPA and subprocessor documentation available on request.
What its label means
This model is served through infrastructure controlled by a US company, which remains subject to the US CLOUD Act even when it runs in an EU region. We label it “fast access”, never sovereign, and it is flagged in the API response before you call it — so the choice is yours, made with full information. If Modal fails (429, 5xx or unreachable), the call automatically falls back to OpenRouter, which then picks the final provider from its own pool — a pool we do not control. The X-Routed-Provider header on every response names the route used.
How we draw the line: GDPR vs. the CLOUD Act →All GLM models and their jurisdiction →Sovereignty Score — 0/100
Deterministic 0–100 score computed from the five factors below — ownership, hosting jurisdiction, cloud-provider control, data retention, deployment control. Full methodology: How Frontière AI determines sovereignty →
- Operating-company ownership
- 0/40
- Hosting jurisdiction (observed)
- 0/30
- Cloud-provider control
- 0/15
- Data retention
- 0/10
- Deployment control
- 0/5
Effective provider assessed: modal.
Calling it
The API is OpenAI-compatible. Change base_url and the key, then use this model id:
client = OpenAI(
base_url="https://getfrontiereai.eu/api/v1",
api_key=os.environ["FRONTIERE_KEY"],
)
reply = client.chat.completions.create(
model="glm-5.3-flash",
messages=[{"role": "user", "content": "Bonjour"}],
)One key covers the whole catalog — you switch models by changing a single string.
API reference →Pricing
The price you see is the price debited from your prepaid balance, margin and VAT included — not an infrastructure cost. No subscription: top up from €10; calls are refused once the balance reaches zero, and a call already running can take it slightly below — deducted from your next top-up.
What will it cost you?
Pick a workload or type your own token counts: the estimate uses the prices above, margin and VAT included.
Example workload
Roughly 1,000 tokens ≈ 750 English words.
No discounted cache rate on this model: every input token is billed at the input rate.
Per request
€0.0018
Per day
€1.83
Per month
€54.81
30 days
A €10 top-up covers about 5,473 requests · GLM-5.3 Flash
Where the money goes
- Input€31.00 · 57%
- Output€23.81 · 43%
Estimate, margin and VAT included, from the prices on this page. You are billed on the tokens the provider reports for each call, debited from a prepaid balance — no subscription.
FAQ
Is GLM-5.3 Flash (Zhipu/Z.ai) GDPR-compliant on Frontière AI?
This model is labeled “fast access”, not sovereign: it is served through Modal, controlled by a US company and therefore subject to the CLOUD Act even in an EU region. For regulated workloads, pick a model from the sovereign tier. In either case, Frontière AI stores neither the prompts nor the completions from API calls. If Modal is unavailable, the call falls back to OpenRouter, which picks the final provider from its own pool.
How much does GLM-5.3 Flash (Zhipu/Z.ai) cost?
€0.0689 per 100,000 input tokens and €0.2268 per 100,000 output tokens — margin and VAT included, that is the amount debited from your prepaid balance. No subscription: you top up from €10; calls are refused once the balance reaches zero, and a call already running can take it slightly below — deducted from your next top-up.
How do I call GLM-5.3 Flash (Zhipu/Z.ai) from my code?
The API is OpenAI-compatible: point base_url at https://getfrontiereai.eu/api/v1, swap the key, and pass “glm-5.3-flash” as the model field. Your SDK, scripts and tools keep working, streaming included.
Under which licence is GLM-5.3 Flash (Zhipu/Z.ai) released?
MIT, a permissive licence. It covers the model weights published by Zhipu / Z.ai; your use through Frontière AI's API is separately governed by our own terms.
Is there any behaviour I should know about?
Reasoning model — thinks before answering. Omit max_tokens or allow at least ~1,000.
Articles about this model
Other models in the catalog
Call it in minutes
Create an account, top up €10, change two lines.