Requesty
Sign in

identity

open weights
DeepInfra logo

glm-5.2DeepInfra

from /1M in$0.60deepinfra inc.
context1M128K out
best ttft2.60sdeepinfra inc.
price spread1.3x2 endpoints
endpoints
2
regions
1
best tok/s
77
api
chat
released
June 2026
eu routing
available

capabilities 4/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 1.3x more on deepinfra inc. than on deepinfra inc.. That is what the endpoints table is for.

endpoints

2 / 1 region
Providers serving glm-5.2, with pricing and measured performance. Best value in each column is coloured.
#flags
1DeepInfra Inc.Global1M$0.60$1.92$0.112.60s77.0zdr
2DeepInfra Inc.Global262K$0.75$2.40$0.142.60s77.0zdr
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 Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**.

questions 7

Which providers serve glm-5.2?
glm-5.2 is available from 1 provider through Requesty: DeepInfra Inc.. 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 $0.60 per million input tokens and $1.92 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 DeepInfra, 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 1M tokens of context, with up to 128K 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 1 provider 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 "deepinfra/glm-5.2:flex" only when you need one specific deployment and want no failover.

more from deepinfra 1

Other DeepInfra models
modelcontextfrom /Mproviders
qwen3.8-2.4T-A95B262K$2.001

route glm-5.2 through one endpoint

One key for 1 provider 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-5.21 provider2 endpointsfrom $0.60 /1M inctx 1Mttft 2.60sspread 1.3xupdated Sep 12