GLM-5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

zhipuai/glm-5

Organization: Zhipu AI
Family: glm
Providers: 30
Context: 204,800
Output limit: 131,072
Knowledge: —
Release: 2026-02-12
Updated: 2026-02-12
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

44 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Abacus	zai-org/GLM-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
Alibaba Token Plan	glm-5	202,752	16,384	$0.00 / $0.00	Yes	Yes	Yes	View
Alibaba Token Plan (China)	glm-5	202,752	16,384	$0.00 / $0.00	Yes	Yes	Yes	View
Amazon Bedrock	zai.glm-5	202,752	131,072	$1.00 / $3.20	Yes	Yes	Yes	View
Cortecs	glm-5	202,752	202,752	$0.988 / $3.164	Yes	Yes	Yes	View
CrossModel	z-ai/glm-5	200,000	128,000	$0.60 / $3.00	Yes	Yes	Yes	View
DevPass (LLM Gateway)	glm-5	203,000	131,072	$0.72 / $2.30	Yes	Yes	—	View
DInference	glm-5	200,000	128,000	$0.75 / $2.40	Yes	Yes	—	View
Eden AI	zai/glm-5	202,752	131,072	$1.00 / $3.20	Yes	Yes	No	View
GMI Cloud	zai-org/GLM-5-FP8	202,752	131,072	$0.60 / $1.92	Yes	Yes	—	View
Impossibl	zai/glm-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
Kilo Gateway	z-ai/glm-5	198,000	128,000	$0.60 / $1.92	Yes	Yes	Yes	View
LLM Gateway	embercloud/glm-5	203,000	131,000	$0.72 / $2.30	Yes	Yes	No	View
LLM Gateway	alibaba/glm-5	202,752	16,384	$0.573 / $2.58	Yes	Yes	No	View
LLM Gateway	novita/glm-5	202,800	131,072	$1.00 / $3.20	Yes	Yes	No	View
LLM Gateway	tencent/glm-5	200,000	128,000	$1.00 / $3.20	Yes	Yes	No	View
LLM Gateway	baidu/glm-5	202,752	131,072	$1.00 / $3.20	Yes	Yes	No	View
LLM Gateway	vertex-openai/glm-5	202,752	32,768	$1.00 / $3.20	Yes	Yes	No	View
LLM Gateway	zai/glm-5	202,800	131,100	$1.00 / $3.20	Yes	Yes	No	View
Melious	glm-5	203,000	131,072	$1.10124 / $3.36168	Yes	Yes	—	View
Merge Gateway	zai/glm-5	200,000	131,072	$1.00 / $3.20	Yes	Yes	No	View
NanoGPT	z-ai/glm-5:thinking	200,000	128,000	$0.50 / $2.55	Yes	Yes	Yes	View
NanoGPT	z-ai/glm-5	200,000	128,000	$0.50 / $2.55	Yes	Yes	Yes	View
Ofox	z-ai/glm-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
Amazon Bedrockvia OpenRouter	z-ai/glm-5 unknown	202,752	131,072	$1.00 / $3.20	Yes	Yes	No	View
Baiduvia OpenRouter	z-ai/glm-5 fp8	202,752	131,072	$0.70 / $2.24	Yes	Yes	Yes	View
GMICloudvia OpenRouter	z-ai/glm-5 fp8	202,752	182,476	$0.60 / $1.92	Yes	Yes	Yes	View
Novitavia OpenRouter	z-ai/glm-5 fp8	202,800	131,072	$1.00 / $3.20	Yes	Yes	No	View
SiliconFlowvia OpenRouter	z-ai/glm-5 fp8	204,800	131,072	$0.95 / $2.55	Yes	Yes	No	View
StreamLakevia OpenRouter	z-ai/glm-5 fp8	198,000	128,000	$0.60 / $1.92	Yes	Yes	Yes	View
Venicevia OpenRouter	z-ai/glm-5 fp8	198,000	32,000	$1.00 / $3.20	Yes	Yes	Yes	View
Z.AIvia OpenRouter	z-ai/glm-5 fp8	202,752	131,072	$1.00 / $3.20	Yes	Yes	No	View
OrcaRouter	z-ai/glm-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
SCNet Token Plan	GLM-5	204,800	131,072	$0.00 / $0.00	Yes	Yes	—	View
Tempr Gateway	zai/glm-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
TensorX	z-ai/glm-5	202,752	202,752	$1.00 / $3.20	Yes	Yes	—	View
Together AI	zai-org/GLM-5	202,752	131,072	$1.00 / $3.20	Yes	Yes	Yes	View
TokenGo	z-ai/glm-5	204,800	131,072	$0.89 / $3.2647	Yes	Yes	—	View
Venice AI	zai-org-glm-5	198,000	32,000	$1.00 / $3.20	Yes	Yes	Yes	View
Vercel AI Gateway	zai/glm-5	202,800	131,100	$1.00 / $3.20	Yes	Yes	—	View
Vertex	zai-org/glm-5-maas	200,000	128,000	$1.00 / $3.20	Yes	Yes	—	View
Vultr	glm-5.x-menthol	202,752	131,072	$0.40 / $1.75	Yes	Yes	—	View
Z.AI	glm-5	204,800	131,072	$1.00 / $3.20	Yes	Yes	—	View
ZenMux	z-ai/glm-5	200,000	128,000	$0.58 / $2.60	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers44Across 30 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 8 lowest-priced configurations

InputOutput

GMICloudgmicloud/fp8

$0.60$1.92

StreamLakestreamlake/fp8

$0.60$1.92

Baidubaidu/fp8

$0.70$2.24

SiliconFlowsiliconflow/fp8

$0.95$2.55

Amazon Bedrockamazon-bedrock

$1.00$3.20

Novitanovita/fp8

$1.00$3.20

Venicevenice/fp8

$1.00$3.20

Z.AIz-ai/fp8

$1.00$3.20

z-ai/glm-5Observed Oct 4, 2026, 11:31 AM UTC

Input: $0.60
Output: $1.92
Cache read: $0.12

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Amazon Bedrockamazon-bedrock	$1.00	$3.20	—	—
Baidubaidu/fp8	$0.70	$2.24	$0.14	—
GMICloudgmicloud/fp8	$0.60	$1.92	$0.12	—
Novitanovita/fp8	$1.00	$3.20	$0.20	—
SiliconFlowsiliconflow/fp8	$0.95	$2.55	$0.20	—
StreamLakestreamlake/fp8	$0.60	$1.92	$0.12	—
Venicevenice/fp8	$1.00	$3.20	$0.20	—
Z.AIz-ai/fp8	$1.00	$3.20	$0.20	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock

947–6,667.43 ms

Baidubaidu/fp8

1,287.5–51,401.8 ms

GMICloudgmicloud/fp8

3,059–127,690.84 ms

Novitanovita/fp8

1,377–7,402.54 ms

SiliconFlowsiliconflow/fp8

2,674–6,098.4 ms

StreamLakestreamlake/fp8

2,707–10,810.48 ms

All latency percentiles 8 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock	947 ms	1,801.75 ms	3,066.1 ms	6,667.43 ms
Baidubaidu/fp8	1,287.5 ms	2,211.5 ms	3,622 ms	51,401.8 ms
GMICloudgmicloud/fp8	3,059 ms	3,955 ms	5,113.2 ms	127,690.84 ms
Novitanovita/fp8	1,377 ms	1,746.5 ms	2,659.6 ms	7,402.54 ms
SiliconFlowsiliconflow/fp8	2,674 ms	3,245.5 ms	3,960 ms	6,098.4 ms
StreamLakestreamlake/fp8	2,707 ms	3,536 ms	5,323.6 ms	10,810.48 ms
Venicevenice/fp8	1,628 ms	2,899.5 ms	5,910.4 ms	17,353.28 ms
Z.AIz-ai/fp8	7,216 ms	7,738 ms	8,276.9 ms	10,281 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock

97–151.55 t/s

Baidubaidu/fp8

48–73.22 t/s

GMICloudgmicloud/fp8

49–94.72 t/s

Novitanovita/fp8

74–108 t/s

SiliconFlowsiliconflow/fp8

51–85 t/s

StreamLakestreamlake/fp8

43–82.8 t/s

All throughput percentiles 8 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock	97 t/s	119 t/s	134 t/s	151.55 t/s
Baidubaidu/fp8	48 t/s	55 t/s	62 t/s	73.22 t/s
GMICloudgmicloud/fp8	49 t/s	58 t/s	68.6 t/s	94.72 t/s
Novitanovita/fp8	74 t/s	81 t/s	86 t/s	108 t/s
SiliconFlowsiliconflow/fp8	51 t/s	62 t/s	70 t/s	85 t/s
StreamLakestreamlake/fp8	43 t/s	52 t/s	60 t/s	82.8 t/s
Venicevenice/fp8	66 t/s	82.5 t/s	98 t/s	112.7 t/s
Z.AIz-ai/fp8	72 t/s	80 t/s	85 t/s	92 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 8 endpoints

Endpoint5 minutes30 minutes24 hours

Amazon Bedrockamazon-bedrockObserved Oct 4, 2026, 11:31 AM UTC

100%

99.46%

Baidubaidu/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

99.62%

GMICloudgmicloud/fp8Observed Oct 4, 2026, 11:31 AM UTC

99.02%

99.86%

99%

Novitanovita/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.99%

SiliconFlowsiliconflow/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.63%

StreamLakestreamlake/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.89%

99.78%

Venicevenice/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.31%

99.37%

Z.AIz-ai/fp8Observed Oct 4, 2026, 11:31 AM UTC

99.8%

99.97%

99.99%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

z-ai/glm-5Observed Oct 4, 2026, 11:31 AM UTC

Design Arena	Category	Elo	Win rate	Rank
agents	androidnative	1,161	55.1%	24
agents	fullstack	1,121	51.7%	27
agents	godotgamedev	1,144	46.7%	21
agents	htmlslides	1,147	45.1%	18
agents	mobileapps	1,133	51.6%	32
models	3d	1,244	56.3%	33
models	asciiart	1,158	47.9%	40
models	codecategories	1,252	55.5%	34
models	dataviz	1,237	53%	39
models	gamedev	1,247	57.4%	34
models	svg	1,167	54.4%	36
models	uicomponent	1,237	53.6%	43
models	website	1,254	55%	36

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondZ.ai: GLM 5

75.397%

tau bench verified airlineZ.ai: GLM 5

76.963%

Evaluation	Configuration	Source	Results	Details
models · uicomponent	GLM 5z-ai/glm-5-20260211	Design Arena	1,237 Elo	Details
models · svg	GLM 5z-ai/glm-5-20260211	Design Arena	1,167 Elo	Details
models · 3d	GLM 5z-ai/glm-5-20260211	Design Arena	1,244 Elo	Details
models · dataviz	GLM 5z-ai/glm-5-20260211	Design Arena	1,237 Elo	Details
models · asciiart	GLM 5z-ai/glm-5-20260211	Design Arena	1,158 Elo	Details
models · gamedev	GLM 5z-ai/glm-5-20260211	Design Arena	1,247 Elo	Details
gpqa diamond	Z.ai: GLM 5z-ai/glm-5-20260211	OpenRouter	75.397%	Details
models · codecategories	GLM 5z-ai/glm-5-20260211	Design Arena	1,252 Elo	Details
tau bench verified airline	Z.ai: GLM 5z-ai/glm-5-20260211	OpenRouter	76.963%	Details
models · website	GLM 5z-ai/glm-5-20260211	Design Arena	1,254 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	z-ai/glm-5-20260211	2–9 turns	$0.022503	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage814,613,850,235 reported tokens · 20 days with observations

98B0

2026-07-07
39,749,438,159 tokens

2026-07-08
34,343,007,806 tokens

2026-07-09
82,345,510,888 tokens

2026-07-10
64,847,418,522 tokens

2026-07-11
23,483,951,563 tokens

2026-07-12
16,480,830,301 tokens

2026-07-13
97,634,771,251 tokens

2026-07-14
21,901,856,247 tokens

2026-07-15
18,729,345,024 tokens

2026-07-16
57,581,370,763 tokens

2026-07-17
32,973,406,263 tokens

2026-07-20
17,482,281,073 tokens

2026-07-22
37,389,716,746 tokens

2026-07-23
67,995,473,893 tokens

2026-07-24
64,972,296,611 tokens

2026-07-25
22,977,651,055 tokens

2026-07-27
25,185,971,871 tokens

2026-07-28
21,667,058,481 tokens

2026-07-30
43,779,709,678 tokens

2026-08-06
23,092,784,040 tokens

Jul 6, 2026Oct 3, 2026

Daily observations · 20 days

Date (UTC)	Reported tokens	Reported routes
Aug 6, 2026	23,092,784,040	1
Jul 30, 2026	43,779,709,678	1
Jul 28, 2026	21,667,058,481	1
Jul 27, 2026	25,185,971,871	1
Jul 25, 2026	22,977,651,055	1
Jul 24, 2026	64,972,296,611	1
Jul 23, 2026	67,995,473,893	1
Jul 22, 2026	37,389,716,746	1
Jul 20, 2026	17,482,281,073	1
Jul 17, 2026	32,973,406,263	1
Jul 16, 2026	57,581,370,763	1
Jul 15, 2026	18,729,345,024	1
Jul 14, 2026	21,901,856,247	1
Jul 13, 2026	97,634,771,251	1
Jul 12, 2026	16,480,830,301	1
Jul 11, 2026	23,483,951,563	1
Jul 10, 2026	64,847,418,522	1
Jul 9, 2026	82,345,510,888	1
Jul 8, 2026	34,343,007,806	1
Jul 7, 2026	39,749,438,159	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

z-ai/glm-5Observed Oct 4, 2026, 11:31 AM UTC

Context: 204,800
Maximum output: 128,000
Tokenizer: Other
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-02-11

Base URLhttps://openrouter.ai/api/v1

Model IDz-ai/glm-5

Version IDz-ai/glm-5-20260211

Weights IDzai-org/GLM-5

Reasoning

Required: No
Enabled by default: Yes
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
logprobs
max_tokens
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Default parameters

top p: 0.95
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GLM-5 cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GLM-5?

There are 44 cataloged offers across 30 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 204,800 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 8823747720db
Sep 12, 2026 · 1bef7a666755