GLM-4.7-Flash

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

zhipuai/glm-4.7-flash

Organization: Zhipu AI
Family: glm-flash
Providers: 26
Context: 200,000
Output limit: 131,072
Knowledge: 2025-04
Release: 2026-01-19
Updated: —
Weights: Open
Input: text
Output: text
Capabilities: —

Providers

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

32 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
AIHubMix	glm-4.7-flash-free	200,000	131,072	— / —	—	—	—	View
AI/ML API	z-ai/glm-4.7-flash	202,752	16,384	— / —	—	—	—	View
Amazon Bedrock	zai.glm-4.7-flash	202,752	131,072	— / —	—	—	—	View
Cloudflare Workers AI	@cf/zai-org/glm-4.7-flash	131,072	131,072	— / —	—	—	—	View
Cortecs	glm-4.7-flash	203,000	203,000	— / —	—	—	—	View
Deep Infra	zai-org/GLM-4.7-Flash	202,752	16,384	— / —	—	—	—	View
DevPass (LLM Gateway)	glm-4.7-flash	200,000	131,072	— / —	—	—	—	View
Eden AI	amazon/zai.glm-4.7-flash	203,000	131,072	— / —	—	—	—	View
Eden AI	cloudflare/@cf/zai-org/glm-4.7-flash	131,072	131,072	— / —	—	—	—	View
Eden AI	amazon/zai.glm-4.7-flash@us	203,000	131,072	— / —	—	—	—	View
Eden AI	deepinfra/zai-org/GLM-4.7-Flash	202,752	131,072	— / —	—	—	—	View
EmpirioLabs AI	glm-4-7-flash	200,000	131,072	— / —	—	—	—	View
Hugging Face	zai-org/GLM-4.7-Flash	200,000	128,000	— / —	—	—	—	View
Jiekou.AI	zai-org/glm-4.7-flash	200,000	128,000	— / —	—	—	—	View
Kenari	glm-4-7-flash:free	200,000	131,072	— / —	—	—	—	View
Kilo Gateway	z-ai/glm-4.7-flash	131,072	117,964	— / —	—	—	—	View
LLM Gateway	embercloud/glm-4.7-flash	200,000	131,000	— / —	—	—	—	View
Merge Gateway	zai/glm-4.7-flash	200,000	128,000	— / —	—	—	—	View
NanoGPT	z-ai/glm-4.7-flash:thinking	200,000	128,000	— / —	—	—	—	View
NanoGPT	z-ai/glm-4.7-flash	200,000	128,000	— / —	—	—	—	View
Novita AI	zai-org/glm-4.7-flash	200,000	128,000	— / —	—	—	—	View
Cloudflarevia OpenRouter	z-ai/glm-4.7-flash unknown	131,072	117,964	$0.0605 / $0.40	Yes	Yes	Yes	View
Novitavia OpenRouter	z-ai/glm-4.7-flash bf16	200,000	128,000	$0.07 / $0.40	Yes	Yes	No	View
Venicevia OpenRouter	z-ai/glm-4.7-flash fp8	128,000	16,384	$0.06 / $0.40	Yes	Yes	Yes	View
Pendra	glm-4.7-flash	200,000	131,072	— / —	—	—	—	View
Poe	novita/glm-4.7-flash	200,000	65,500	— / —	—	—	—	View
Synthetic	hf:zai-org/GLM-4.7-Flash	196,608	65,536	— / —	—	—	—	View
Tempr Gateway	zai/glm-4.7-flash	200,000	131,072	— / —	—	—	—	View
Vercel AI Gateway	zai/glm-4.7-flash	200,000	131,000	— / —	—	—	—	View
Z.AI	glm-4.7-flash	200,000	131,072	— / —	—	—	—	View
ZenMux	z-ai/glm-4.7-flash-free	200,000	128,000	— / —	—	—	—	View
Zhipu AI	glm-4.7-flash	200,000	131,072	— / —	—	—	—	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$0.06Per 1M input tokens

Output from$0.40Per 1M output tokens

Available offers32Across 26 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 · 3 lowest-priced configurations

InputOutput

Venicevenice/fp8

$0.06$0.40

Cloudflarecloudflare

$0.0605$0.40

Novitanovita/bf16

$0.07$0.40

z-ai/glm-4.7-flashObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.0605
Output: $0.40

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Cloudflarecloudflare	$0.0605	$0.40	—	—
Novitanovita/bf16	$0.07	$0.40	$0.01	—
Venicevenice/fp8	$0.06	$0.40	$0.01	—

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 · 3 endpoints

P50P75P90P99

Cloudflarecloudflare

402–9,903.31 ms

Novitanovita/bf16

1,139–15,369.04 ms

Venicevenice/fp8

1,143–5,823.12 ms

All latency percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Cloudflarecloudflare	402 ms	629 ms	1,627.9 ms	9,903.31 ms
Novitanovita/bf16	1,139 ms	2,688.75 ms	8,147.4 ms	15,369.04 ms
Venicevenice/fp8	1,143 ms	1,502 ms	2,165 ms	5,823.12 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

Cloudflarecloudflare

48–94 t/s

Novitanovita/bf16

49–104.42 t/s

Venicevenice/fp8

27–46 t/s

All throughput percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Cloudflarecloudflare	48 t/s	58 t/s	68 t/s	94 t/s
Novitanovita/bf16	49 t/s	66 t/s	78 t/s	104.42 t/s
Venicevenice/fp8	27 t/s	32 t/s	36.7 t/s	46 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 · 3 endpoints

Endpoint5 minutes30 minutes24 hours

CloudflarecloudflareObserved Oct 10, 2026, 11:31 AM UTC

100%

Novitanovita/bf16Observed Oct 10, 2026, 11:31 AM UTC

6.04%

Venicevenice/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

96.74%

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-4.7-flashObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 20

Intelligence

14.9

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,126	51.2%	77
models	codecategories	1,181	53.1%	61
models	dataviz	1,126	45.3%	89
models	gamedev	1,142	49.7%	75
models	svg	1,037	44.2%	75
models	uicomponent	1,211	57.6%	50
models	website	1,199	54%	60

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

tau bench verified airlineZ.ai: GLM 4.7 Flash

67.467%

gpqa diamondZ.ai: GLM 4.7 Flash

52.381%

Evaluation	Configuration	Source	Results	Details
models · dataviz	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,123 Elo	Details
models · codecategories	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,178 Elo	Details
Composite indices	GLM-4.7-Flash (Reasoning)z-ai/glm-4.7-flash-20260119	Artificial Analysis	Intelligence 14.9 · Coding — · Agentic —	Details
models · gamedev	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,135 Elo	Details
models · 3d	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,121 Elo	Details
models · svg	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,038 Elo	Details
models · website	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,194 Elo	Details
tau bench verified airline	Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	OpenRouter	67.467%	Details
models · uicomponent	GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	Design Arena	1,205 Elo	Details
gpqa diamond	Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash-20260119	OpenRouter	52.381%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

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

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	z-ai/glm-4.7-flash-20260119	2–9 turns	$0.003146	Details

Source: OpenRouter, as of Oct 20, 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.

Technical details & API

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

Current route specifications

z-ai/glm-4.7-flashObserved Oct 10, 2026, 11:31 AM UTC

Context: 200,000
Maximum output: 117,964
Tokenizer: Other
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-01-19

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

Model IDz-ai/glm-4.7-flash

Version IDz-ai/glm-4.7-flash-20260119

Weights IDzai-org/GLM-4.7-Flash

Reasoning

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

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
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-4.7-Flash cost?

Listed rates start at $0.06 per million input tokens and $0.40 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GLM-4.7-Flash?

There are 32 cataloged offers across 26 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: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 3 recorded revisions

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

Oct 20, 2026 · 0ef398ed1687
Sep 14, 2026 · 300eec66fd9d
Sep 12, 2026 · 52e1bbb431a6