Requesty
Sign in

identity

open weights
Z.AI logo

glm-5.2Z.AI

from /1M in$0.80runware inc.
context1.0M1.0M out
best ttft72mssference
price spread2.6x12 endpoints
endpoints
12
regions
2
best tok/s
150
api
chat
released
June 2026
eu routing
available

capabilities 4/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 2.6x more on scaleway sas than on runware inc.. That is what the endpoints table is for.

endpoints

12 / 2 regions
Providers serving glm-5.2, with pricing and measured performance. Best value in each column is coloured.
#flags
1Runware Inc.Global1.0M$0.80$2.55$0.163.07s97.0zdr
2Sail Research Co.Global1.0M$0.80$3.00$0.16---zdr
3DoublewordGlobal1.0M$1.05$3.30-1.84s-no-train
4Inceptron ABEU1M$1.20$4.20$0.261.41s62.0zdr
5sferenceEU1.0M$1.20$4.20$0.2672ms150.0zdr
6DoublewordGlobal1.0M$1.40$4.40-1.84s-no-train
7Fireworks AIGlobal1M$1.40$4.40$0.141.32s82.0zdr
8Nebius AIEU1M$1.40$4.40free16.07s134.0zdr
9Z.aiGlobal1M$1.40$4.40$0.264.47s59.0zdr
10TensorX Ltd.EU1.0M$1.50$4.50$0.381.11s124.0zdr
11Mistral AI SASEU1M$1.54$4.84$0.15---zdr
12Scaleway SASEU256K$2.09$6.38-1.60s--zdr
provider price, no markupper 1M tokensblank where no qualifying sample

measured

through Sep 12
median
-3262ms16.49s36.25s07-0608-0309-0710.48s5.98s2.22s1.71s1.48s1.36s1.25s990ms423ms90ms
hover the plot for weekly values
time to first token per provider: current value, window low and high, and change across the window
providernowlowhighchange
sference72ms30ms506ms-82%
TensorX Ltd.1.11s990ms2.11s-13%
Fireworks AI1.32s1.09s1.54s+8.6%
Inceptron AB1.41s423ms1.34s-68%
Scaleway SAS1.60s385ms1.36s+253%
Doubleword1.84s874ms10.48s+321%
DeepInfra Inc.2.60s874ms1.83s-6.9%
Runware Inc.3.07s1.31s2.22s+69%
Z.ai4.47s2.98s5.98s+24%
Nebius AI16.07s556ms32.95s-67%

median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.

Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
τ²-Bench99.1
GPQA Diamond89.5
Coding Index68.8
SciCode51.2
Terminal-Bench Hard50.8
Humanity's Last Exam41.1
Intelligence Index38.6
7 evalsmean62.7

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-06-16.

call it

model=
glm-5.2

requesty routes this id across every provider serving glm-5.2, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it

Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.

quickstart

openai compatible
main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="glm-5.2",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models

notes

reference

GLM 5.2 is the latest Z.ai flagship model for long horizon coding, reasoning, and agentic workflows. It improves on GLM 5.1 with a 1M token context window, stronger engineering task performance, multiple thinking effort levels, and architectural changes that reduce long context inference cost while improving speculative decoding. Released under the MIT license, it is designed for sustained work over large repositories, complex tool use, and multi step technical tasks.

questions 7

Which providers serve glm-5.2?
glm-5.2 is available from 11 providers through Requesty: Runware Inc., Sail Research Co., Doubleword, Inceptron AB, sference, Fireworks AI. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does glm-5.2 cost?
Pricing starts at $0.80 per million input tokens and $2.55 per million output tokens on the cheapest provider. Prices vary by provider and region; the table above shows every endpoint. Requesty charges exactly what the upstream provider charges, with no markup.
Is glm-5.2 open weights?
Yes. glm-5.2 is an open-weights model from Z.AI, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of glm-5.2?
glm-5.2 supports up to 1.0M tokens of context, with up to 1.0M output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for glm-5.2?
In recent production traffic through Requesty, sference had the lowest median time to first token (72ms) for glm-5.2. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use glm-5.2 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "glm-5.2" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call glm-5.2 by its managed id or a provider id?
Use the managed id, "glm-5.2". Requesty picks which of the 11 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "glm-5.2@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "runware/glm-5.2" only when you need one specific deployment and want no failover.

more from z.ai 6

Other Z.AI models
modelcontextfrom /Mproviders
glm-5.3-flash1.0M$0.077
glm-5.31.0M$1.206
glm-5.2-fast1M$2.101
glm-5.1205K$0.845
glm-5203K$1.002
glm-4.7200K$0.601

route glm-5.2 through one endpoint

One key for 11 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology

glm-5.211 providers12 endpointsfrom $0.80 /1M inctx 1.0Mttft 72msspread 2.6xupdated Sep 12