Zhipu AI model product
GLM 4.7 Flash
7 Flash is a high-speed, cost-efficient LLM from Zhipu AI optimized for fast inference and lower latency.
Updated Oct 23, 2026. Default version: GLM-4.7-Flash
LLMBoard Score35.7GLM-4.7-Flash
Coverage60%6 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
GLM 4.7 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 4.7 Flash Benchmark Results
Benchmark scores for GLM-4.7-Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTau-bench | Score79.50% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score91.60% | Rank43 | Participants122 | Percentile65.29% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score42.80% | Rank62 | Participants70 | Percentile11.59% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score60.82% | Rank73 | Participants168 | Percentile56.89% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score14.40% | Rank89 | Participants109 | Percentile18.52% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score59.20% | Rank93 | Participants120 | Percentile22.69% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score0.29% | Rank111 | Participants200 | Percentile44.72% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score75.20% | Rank122 | Participants256 | Percentile52.55% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,369.38 rating | Rank124 | Participants131 | Percentile5.38% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score7.60% | Rank135 | Participants200 | Percentile32.66% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score41.67% | Rank137 | Participants193 | Percentile29.17% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,364.55 rating | Rank143 | Participants218 | Percentile34.56% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,350.60 rating | Rank147 | Participants218 | Percentile32.72% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score16.15% | Rank161 | Participants201 | Percentile20.00% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score58.08% | Rank161 | Participants199 | Percentile19.19% | EvidenceB | EvaluatedN/A |
GLM 4.7 Flash Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryrussian | Rank104 | Rating / score1,364.18 | Votes1,059 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank110 | Rating / score1,396.33 | Votes1,205 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank114 | Rating / score1,368.05 | Votes1,304 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank115 | Rating / score1,325.09 | Votes1,380 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank116 | Rating / score1,375.83 | Votes1,466 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank119 | Rating / score1,340.00 | Votes1,739 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank119 | Rating / score1,376.93 | Votes2,316 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank120 | Rating / score1,422.60 | Votes1,760 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank121 | Rating / score1,405.62 | Votes1,597 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank122 | Rating / score1,415.07 | Votes3,639 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank122 | Rating / score1,355.72 | Votes2,338 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank124 | Rating / score1,389.54 | Votes4,248 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank124 | Rating / score1,347.93 | Votes7,226 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank124 | Rating / score1,369.38 | Votes11,884 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank125 | Rating / score1,337.57 | Votes8,239 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank125 | Rating / score1,386.66 | Votes6,560 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank128 | Rating / score1,402.88 | Votes821 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank132 | Rating / score1,409.74 | Votes821 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank133 | Rating / score1,388.99 | Votes4,288 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank133 | Rating / score1,420.29 | Votes4,288 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank134 | Rating / score1,335.96 | Votes228 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank135 | Rating / score1,282.92 | Votes239 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank135 | Rating / score1,343.57 | Votes228 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank135 | Rating / score1,296.39 | Votes239 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank136 | Rating / score1,382.47 | Votes2,794 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank137 | Rating / score1,390.97 | Votes4,649 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank139 | Rating / score1,350.32 | Votes439 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank139 | Rating / score1,367.87 | Votes2,244 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank140 | Rating / score1,422.87 | Votes2,794 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank140 | Rating / score1,363.89 | Votes439 | ObservationsN/A | Result date |
GLM 4.7 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.06 input, $0.40 output per 1M via Deep Infra
- Tracked offerings
- 21
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderHugging Face | Provider model IDzai-org/GLM-4.7-Flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderZ.AI | Provider model IDglm-4.7-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderZhipu AI | Provider model IDglm-4.7-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderPendra | Provider model IDglm-4.7-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderEmpirioLabs AI | Provider model IDglm-4-7-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderTempr Gateway | Provider model IDzai/glm-4.7-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context200K | Updated |
| ProviderDeep Infra | Provider model IDzai-org/GLM-4.7-Flash | Regionglobal | Input / 1M$0.06 | Output / 1M$0.40 | Context202.8K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-4.7-flash | Regionglobal | Input / 1M$0.06 | Output / 1M$0.40 | Context200K | Updated |
| ProviderCloudflare Workers AI | Provider model ID@cf/zai-org/glm-4.7-flash | Regionglobal | Input / 1M$0.0605 | Output / 1M$0.40 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-4.7-flash | Regionglobal | Input / 1M$0.0605 | Output / 1M$0.40 | Context200K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-4.7-flash | Regionglobal | Input / 1M$0.0605 | Output / 1M$0.40 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context200K | Updated |
| ProviderJiekou.AI | Provider model IDzai-org/glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context200K | Updated |
| ProviderAmazon Bedrock | Provider model IDzai.glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context202.8K | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context200K | Updated |
| ProviderNovita AI | Provider model IDzai-org/glm-4.7-flash | Regionglobal | Input / 1M$0.07 | Output / 1M$0.40 | Context200K | Updated |
| ProviderPoe | Provider model IDnovita/glm-4.7-flash | Regionglobal | Input / 1M$0.0707 | Output / 1M$0.404 | Context200K | Updated |
| ProviderCortecs | Provider model IDglm-4.7-flash | Regionglobal | Input / 1M$0.08 | Output / 1M$0.478 | Context203K | Updated |
| ProviderSynthetic | Provider model IDhf:zai-org/GLM-4.7-Flash | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context196.6K | Updated |
| ProviderAI/ML API | Provider model IDz-ai/glm-4.7-flash | Regionglobal | Input / 1M$0.1323 | Output / 1M$0.529 | Context202.8K | Updated |
GLM 4.7 Flash Runtime Performance
Provider-specific output speed and catalog latency for GLM-4.7-Flash. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderZAI | Output Speed50.00 tok/s | Catalog Latency2.00 s | Max Input128K | Max Output16.4K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 4.7 Flash Specifications
Technical details for the model's default version.
- Version
- GLM-4.7-Flash
- Released
- Jan 19, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 30B
- Context window
- 128K
- Max output
- 16.4K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
GLM 4.7 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGLM-4.7-Flash | Released | LLMBoard35.70 | Parameters30B | Context128K | Max output16.4K | Open weightsNo | LicenseMIT |
Models similar to GLM 4.7 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 4.5 Air
Zhipu AI
ZA
GLM 4.5
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5
Zhipu AI
What is GLM 4.7 Flash?
Key information about GLM 4.7 Flash and its available data.
7's coding capabilities, including thinking before acting, preserved reasoning across turns, and per-request thinking control. It is designed for coding, agentic workflows, and general reasoning tasks.
Data as of 2026-10-22.
FAQ
Common questions about GLM 4.7 Flash.
When was GLM 4.7 Flash released?
GLM 4.7 Flash's default version was released on Jan 19, 2026.
How much does GLM 4.7 Flash cost?
No official standard PAYG price is currently available for GLM 4.7 Flash. The lowest tracked third-party offer starts at $0.06 input and $0.40 output via Deep Infra.
Who created GLM 4.7 Flash?
GLM 4.7 Flash was created by Zhipu AI.
What is the context window for GLM 4.7 Flash?
The default version has a 128K token context window.
Is GLM 4.7 Flash open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GLM 4.7 Flash?
21 provider offerings are linked to the default version.