GLM-5V-Turbo

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.

zhipuai/glm-5v-turbo

Organization: Zhipu AI
Family: glm
Providers: 13
Context: 200,000
Output limit: 131,072
Knowledge: —
Release: 2026-04-01
Updated: 2026-04-01
Weights: Closed
Input: text, image, video, pdf
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

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

14 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Cortecs	glm-5v-turbo	202,752	202,752	$1.186 / $3.955	Yes	Yes	Yes	View
DevPass (LLM Gateway)	glm-5v-turbo	200,000	131,072	$1.20 / $4.00	Yes	Yes	—	View
Eden AI	zai/glm-5v-turbo	202,752	131,072	$1.20 / $4.00	Yes	Yes	Yes	View
Kilo Gateway	z-ai/glm-5v-turbo	202,752	131,072	$1.20 / $4.00	Yes	Yes	No	View
LLM Gateway	tencent/glm-5v-turbo	200,000	128,000	$1.20 / $4.00	Yes	Yes	No	View
NanoGPT	z-ai/glm-5v-turbo	202,800	131,072	$1.20 / $4.00	No	Yes	Yes	View
NanoGPT	z-ai/glm-5v-turbo:thinking	202,800	131,072	$1.20 / $4.00	Yes	Yes	Yes	View
Ofox	z-ai/glm-5v-turbo	200,000	131,072	$1.20 / $4.00	Yes	Yes	—	View
Z.AIvia OpenRouter	z-ai/glm-5v-turbo fp8	202,752	131,072	$1.20 / $4.00	Yes	Yes	No	View
Tempr Gateway	zai/glm-5v-turbo	200,000	131,072	$1.20 / $4.00	Yes	Yes	—	View
TensorX	z-ai/glm-5v-turbo	202,752	131,072	$1.20 / $4.00	Yes	Yes	—	View
Venice AI	z-ai-glm-5v-turbo	200,000	32,768	$1.50 / $5.00	Yes	Yes	Yes	View
Vercel AI Gateway	zai/glm-5v-turbo	200,000	128,000	$1.20 / $4.00	Yes	Yes	—	View
ZenMux	z-ai/glm-5v-turbo	200,000	128,000	$0.726 / $3.1946	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$0.726Per 1M input tokens

Output from$3.1946Per 1M output tokens

Available offers14Across 13 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 · 1 lowest-priced configuration

InputOutput

Z.AIz-ai/fp8

$1.20$4.00

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

Input: $1.20
Output: $4.00
Cache read: $0.24

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Z.AIz-ai/fp8	$1.20	$4.00	$0.24	—

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 · 1 endpoint

P50P75P90P99

Z.AIz-ai/fp8

3,081–41,961 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Z.AIz-ai/fp8	3,081 ms	8,240 ms	18,339.4 ms	41,961 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Z.AIz-ai/fp8

35–67.53 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Z.AIz-ai/fp8	35 t/s	49 t/s	55 t/s	67.53 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 · 1 endpoint

Endpoint5 minutes30 minutes24 hours

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

—

100%

99.94%

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-5v-turboObserved Oct 4, 2026, 11:31 AM UTC

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,102	42.6%	23
agents	agentichtmlslides	1,134	41.7%	7
agents	agenticslides	1,171	51.6%	5
agents	agenticslides(html)	1,137	41.8%	7
agents	agenticslides(python-pptx)	1,183	53.9%	5
agents	androidnative	1,267	54.8%	4
agents	fullstack	1,147	52%	26
agents	godotgamedev	957	26.9%	35
agents	htmlslides	1,120	44.6%	21
agents	mobileapps	1,131	50.4%	33
agents	pptxslides	1,164	52.1%	5
agents	python-pptxslides	1,165	51.9%	20
agents	webapps	1,117	44.7%	31
models	3d	1,225	52.8%	37
models	asciiart	1,128	43%	53
models	codecategories	1,235	50.1%	43
models	dataviz	1,209	47.7%	51
models	gamedev	1,231	50.7%	39
models	svg	1,151	49.2%	42
models	uicomponent	1,220	48.6%	47
models	website	1,237	49.2%	43

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

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
models · gamedev	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,231 Elo	Details
models · svg	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,151 Elo	Details
models · website	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,237 Elo	Details
models · asciiart	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,128 Elo	Details
models · codecategories	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,235 Elo	Details
models · uicomponent	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,220 Elo	Details
models · 3d	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,225 Elo	Details
models · dataviz	GLM 5V Turboz-ai/glm-5v-turbo-20260401	Design Arena	1,209 Elo	Details

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

Technical details & API

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

Current route specifications

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

Context: 202,752
Maximum output: 131,072
Tokenizer: Other
Input: image, text, video
Output: text
Moderation: No
Added to OpenRouter: 2026-04-01

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

Model IDz-ai/glm-5v-turbo

Version IDz-ai/glm-5v-turbo-20260401

Reasoning

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

Supported parameters

include_reasoning
max_tokens
reasoning
response_format
temperature
tool_choice
tools
top_k
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-5V-Turbo cost?

Listed rates start at $0.726 per million input tokens and $3.1946 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GLM-5V-Turbo?

There are 14 cataloged offers across 13 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 200,000 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.

Catalog history · 2 recorded revisions

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

Sep 14, 2026 · 1f1e1ad68bb2
Sep 12, 2026 · 967adb8e9cbc