GLM 5.2

Z.aitext → textHugging Face OpenRouter

The cheapest provider for GLM 5.2 is InferenceNet at $0.614 per 1M tokens (blended), charging $0.085 per 1M input and $2.20 per 1M output tokens. 26 providers serve it; the most expensive charges 6.0× as much. Context window: 1M tokens. Prices tracked since Oct 3, 2026.

Best price

$0.614

at InferenceNet

Input / output

$0.085 / $2.20

per 1M tokens

Providers

6.0× spread

7 days

—

best price

30 days

—

best price

Context

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for Z.ai: GLM 5.2, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
InferenceNetCheapest	$0.085	$2.20	$0.614	best	1M	99.9%	Oct 3
StreamLake fp8·−60% discount	$0.556	$1.75	$0.853	+39%	1M	99.3%	Oct 3
DeepInfra fp4·−25% discount	$0.563	$1.80	$0.872	+42%	1M	99.6%	Oct 3
Decart mxfp4·−40% discount	$0.39	$2.40	$0.893	+45%	1M	99.2%	Oct 3
Relace	$0.0845	$3.50	$0.938	+53%	1M	99.8%	Oct 3
Morph fp8	$0.232	$3.067	$0.941	+53%	1M	96.7%	Oct 3
Novita fp8·−54% discount	$0.65	$2.04	$0.998	+63%	1M	99.6%	Oct 3
DigitalOcean	$0.70	$2.20	$1.075	+75%	256K	99.7%	Oct 3
SiliconFlow fp8·−50% discount	$0.70	$2.20	$1.075	+75%	1M	99.9%	Oct 3
CoreWeave fp4	$0.76	$2.42	$1.175	+91%	1M	99.9%	Oct 3
Wafer	$0.41	$3.99	$1.305	+113%	1M	99.9%	Oct 3
AtlasCloud fp8·−33% discount	$0.938	$2.948	$1.44	+135%	1M	98.1%	Oct 3
Alibaba fp8	$0.966	$3.036	$1.48	+142%	1M	99.8%	Oct 3
Phala fp8	$1.26	$3.00	$1.695	+176%	1M	99.9%	Oct 3
Cloudflare	$1.18	$4.40	$1.985	+223%	256K	100%	Oct 3
Inceptron fp4	$1.25	$4.39	$2.035	+232%	1M	99.3%	Oct 3
Baidu fp8	$1.40	$4.40	$2.15	+250%	1M	99.9%	Oct 3
BaseTen fp8	$1.40	$4.40	$2.15	+250%	1M	99.8%	Oct 3
Fireworks	$1.40	$4.40	$2.15	+250%	1M	0.0%	Oct 3
Friendli	$1.40	$4.40	$2.15	+250%	1M	99.9%	Oct 3
GMICloud fp8	$1.40	$4.40	$2.15	+250%	1M	99.0%	Oct 3
Mistralzdr nvfp4	$1.40	$4.40	$2.15	+250%	1M	100%	Oct 3
Parasail fp4	$1.40	$4.40	$2.15	+250%	256K	99.8%	Oct 3
Together	$1.40	$4.40	$2.15	+250%	1M	99.3%	Oct 3
Venice fp8	$1.40	$4.40	$2.15	+250%	1M	99.1%	Oct 3
Z.AI fp8	$1.40	$4.40	$2.15	+250%	1M	99.9%	Oct 3
Mistraleu	$1.54	$4.84	$2.365	+285%	1M	100%	Oct 3
BaseTenfast fp8	$2.10	$6.60	$3.225	+425%	1M	100%	Oct 3
Alibabafast fp8	$2.31	$7.26	$3.55	+478%	1M	99.7%	Oct 3
Baidufast fp4	$2.25	$7.88	$3.66	+496%	1M	100%	Oct 3
Decartfast fp4	$2.25	$8.00	$3.69	+501%	1M	100%	Oct 3

InferenceNetCheapest
$0.614
$0.085 in · $2.20 out
best
1M ctx99.9% uptime
StreamLake
$0.853
$0.556 in · $1.75 out
+39%
1M ctx99.3% uptimefp8·−60% discount
DeepInfra
$0.872
$0.563 in · $1.80 out
+42%
1M ctx99.6% uptimefp4·−25% discount
Decart
$0.893
$0.39 in · $2.40 out
+45%
1M ctx99.2% uptimemxfp4·−40% discount
Relace
$0.938
$0.0845 in · $3.50 out
+53%
1M ctx99.8% uptime
Morph
$0.941
$0.232 in · $3.067 out
+53%
1M ctx96.7% uptimefp8
Novita
$0.998
$0.65 in · $2.04 out
+63%
1M ctx99.6% uptimefp8·−54% discount
DigitalOcean
$1.075
$0.70 in · $2.20 out
+75%
256K ctx99.7% uptime
SiliconFlow
$1.075
$0.70 in · $2.20 out
+75%
1M ctx99.9% uptimefp8·−50% discount
CoreWeave
$1.175
$0.76 in · $2.42 out
+91%
1M ctx99.9% uptimefp4
Wafer
$1.305
$0.41 in · $3.99 out
+113%
1M ctx99.9% uptime
AtlasCloud
$1.44
$0.938 in · $2.948 out
+135%
1M ctx98.1% uptimefp8·−33% discount
Alibaba
$1.48
$0.966 in · $3.036 out
+142%
1M ctx99.8% uptimefp8
Phala
$1.695
$1.26 in · $3.00 out
+176%
1M ctx99.9% uptimefp8
Cloudflare
$1.985
$1.18 in · $4.40 out
+223%
256K ctx100% uptime
Inceptron
$2.035
$1.25 in · $4.39 out
+232%
1M ctx99.3% uptimefp4
Baidu
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.9% uptimefp8
BaseTen
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.8% uptimefp8
Fireworks
$2.15
$1.40 in · $4.40 out
+250%
1M ctx0.0% uptime
Friendli
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.9% uptime
GMICloud
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.0% uptimefp8
Mistral
zdr
$2.15
$1.40 in · $4.40 out
+250%
1M ctx100% uptimenvfp4
Parasail
$2.15
$1.40 in · $4.40 out
+250%
256K ctx99.8% uptimefp4
Together
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.3% uptime
Venice
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.1% uptimefp8
Z.AI
$2.15
$1.40 in · $4.40 out
+250%
1M ctx99.9% uptimefp8
Mistral
eu
$2.365
$1.54 in · $4.84 out
+285%
1M ctx100% uptime
BaseTen
fast
$3.225
$2.10 in · $6.60 out
+425%
1M ctx100% uptimefp8
Alibaba
fast
$3.55
$2.31 in · $7.26 out
+478%
1M ctx99.7% uptimefp8
Baidu
fast
$3.66
$2.25 in · $7.88 out
+496%
1M ctx100% uptimefp4
Decart
fast
$3.69
$2.25 in · $8.00 out
+501%
1M ctx100% uptimefp4

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
InferenceNet	$0.075
StreamLake	$0.103
DeepInfra, DigitalOcean	$0.105
Decart	$0.15
Relace	$0.0845
Morph	$0.196
Novita	$0.121
SiliconFlow	$0.13
CoreWeave, BaseTen +2	$0.14
Wafer, Cloudflare +7	$0.26
AtlasCloud	$0.174
Alibaba	$0.193
Phala	$0.22
Inceptron	$0.23
Mistral (eu)	$0.154
BaseTen (fast)	$0.21
Alibaba (fast)	$0.462
Baidu (fast)	$0.56
Decart (fast)	$0.48

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Released: Jun 16, 2026
First tracked: Oct 3, 2026
Canonical slug: z-ai/glm-5.2-20260616
Weights: zai-org/GLM-5.2