Z.ai: GLM 5.3 Flash
z-ai/glm-5.3-flash
Model weightsGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $0.0600 | $0.3000 | $0.0300 | 0.62s | 136 tok/s | ||
| $0.0399 | $0.0784 | $0.0300 | 0.82s | 94 tok/s | ||
| $0.1125 | $0.3750 | $0.0300 | 0.77s | 136 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.60s | 143 tok/s | ||
| $0.0420 | $0.1840 | $0.0410 | 0.44s | 107 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.69s | 137 tok/s | ||
| $0.1200 | $0.5000 | $0.0400 | 0.67s | 139 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.37s | 119 tok/s | ||
| $0.1080 | $0.3500 | $0.0350 | 0.36s | 108 tok/s | ||
| $0.1080 | $0.3500 | $0.0350 | 0.34s | 104 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 1.22s | 129 tok/s | ||
| $0.1200 | $0.3000 | $0.0300 | 0.89s | 90 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.63s | 99 tok/s | ||
| $0.0650 | $0.2400 | $0.0640 | 0.55s | 105 tok/s | ||
| $0.1400 | $0.2400 | $0.0300 | 0.88s | 77 tok/s | ||
| $0.0960 | $0.3200 | $0.0192 | 0.99s | 74 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 1.04s | 82 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.99s | 97 tok/s | ||
| $0.1750 | $0.4700 | $0.0400 | 0.55s | 89 tok/s | ||
| $0.2250 | $0.7500 | $0.0450 | 0.53s | 144 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 1.50s | 90 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.92s | 96 tok/s | ||
| $0.1200 | $0.4500 | $0.0300 | 1.21s | 56 tok/s | ||
| $0.0750 | $0.2500 | $0.0150 | 2.44s | 48 tok/s | ||
| $0.0800 | $0.5000 | $0.0120 | 0.71s | 40 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 2.02s | 48 tok/s | ||
41% off | $0.15$0.0885 | $0.50$0.2950 | $0.03$0.0177 | 1.85s | 36 tok/s | |
44% off | $0.15$0.0840 | $0.50$0.2800 | $0.03$0.0168 | 2.81s | 41 tok/s | |
Fast | $0.1875 | $0.6250 | $0.0375 | 0.75s | 104 tok/s | |
| $0.1750 | $0.6250 | $0.0225 | 1.48s | 38 tok/s | ||
| $0.1750 | $0.6250 | $0.0225 | 1.64s | 39 tok/s | ||
| $0.0480 | $0.1380 | $0.0240 | 1.24s | 23 tok/s | ||
| $0.1200 | $0.3800 | $0.0200 | 0.65s | 164 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.78s | 102 tok/s | ||
| $0.1000 | $0.4000 | $0.0300 | 1.29s | 74 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 1.21s | 63 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 2.27s | 43 tok/s | ||
50% off | $0.15$0.0750 | $0.50$0.2500 | $0.03$0.0150 | 2.79s | 27 tok/s | |
| $0.1500 | $0.5000 | $0.0300 | 0.67s | 70 tok/s | ||
| $0.0650 | $0.1800 | $0.0120 | 9.19s | 9 tok/s | ||
| $0.1500 | $0.5000 | $0.0300 | 0.85s | 49 tok/s | ||
| $0.1000 | $0.5000 | $0.0300 | 1.20s | 165 tok/s |
- Input $0.06 / Output $0.30136 tok/s99.89% uptime
- Input $0.0399 / Output $0.078494 tok/s100.00% uptime
- Input $0.1125 / Output $0.375136 tok/s100.00% uptime
- Input $0.15 / Output $0.50143 tok/s100.00% uptime
- Input $0.042 / Output $0.184107 tok/s100.00% uptime
Input $0.15 / Output $0.50137 tok/s100.00% uptime- Input $0.12 / Output $0.50139 tok/s100.00% uptime
- Input $0.15 / Output $0.50119 tok/s100.00% uptime
- Input $0.108 / Output $0.35108 tok/s100.00% uptime
- Input $0.108 / Output $0.35104 tok/s100.00% uptime
Input $0.15 / Output $0.50129 tok/s99.78% uptime- Input $0.12 / Output $0.3090 tok/s99.77% uptime
- Input $0.15 / Output $0.5099 tok/s100.00% uptime
- Input $0.065 / Output $0.24105 tok/s100.00% uptime
- Input $0.14 / Output $0.2477 tok/s100.00% uptime
- Input $0.096 / Output $0.3274 tok/s99.97% uptime
Input $0.15 / Output $0.5082 tok/s100.00% uptime- Input $0.15 / Output $0.5097 tok/s99.97% uptime
- Input $0.175 / Output $0.4789 tok/s99.97% uptime
Input $0.225 / Output $0.75144 tok/s94.56% uptime
Input $0.15 / Output $0.5090 tok/s99.23% uptime- Input $0.15 / Output $0.5096 tok/s99.83% uptime
- Input $0.12 / Output $0.4556 tok/s100.00% uptime
- Input $0.075 / Output $0.2548 tok/s99.68% uptime
Input $0.08 / Output $0.5040 tok/s99.97% uptime- Input $0.15 / Output $0.5048 tok/s100.00% uptime
- Input $0.0885 / Output $0.29541% off36 tok/s99.86% uptime
- Input $0.084 / Output $0.2844% off41 tok/s100.00% uptime
- Input $0.1875 / Output $0.625104 tok/s99.67% uptimeFast
- Input $0.175 / Output $0.62538 tok/s100.00% uptime
- Input $0.175 / Output $0.62539 tok/s100.00% uptime
- Input $0.048 / Output $0.13823 tok/s100.00% uptime
- Input $0.12 / Output $0.38164 tok/s96.35% uptime
- Input $0.15 / Output $0.50102 tok/s100.00% uptime
- Input $0.10 / Output $0.4074 tok/s99.16% uptime
- Input $0.15 / Output $0.5063 tok/s100.00% uptime
- Input $0.15 / Output $0.5043 tok/s98.27% uptime
- Input $0.075 / Output $0.2550% off27 tok/s99.80% uptime
- Input $0.15 / Output $0.5070 tok/s99.44% uptime
Input $0.065 / Output $0.189 tok/s97.02% uptime- Input $0.15 / Output $0.5049 tok/s99.96% uptime
- Input $0.10 / Output $0.50165 tok/s99.74% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
GLM 5.3 Flash — Price history
| $0.0268 | $0.4995 | 78.3% | 2.0% | ||
| $0.0269 | $0.3204 | 90.1% | 3.6% | ||
| $0.0277 | $0.2498 | 78.8% | 0.5% | ||
| $0.0310 | $0.0778 | 89.9% | 7.3% | ||
| $0.0348 | $0.2997 | 84.1% | 5.5% | ||
| $0.0358 | $0.3796 | 84.2% | 4.4% | ||
| $0.0366 | $0.4996 | 90.5% | 1.6% | ||
| $0.0379 | $0.1786 | 51.1% | 0.0% | ||
| $0.0402 | $0.3491 | 92.8% | 6.1% | ||
| $0.0412 | $0.1833 | 73.6% | 3.6% | ||
| $0.0418 | $0.3493 | 90.7% | 2.0% | ||
| $0.0418 | $0.4997 | 90.1% | 8.8% | ||
| $0.0422 | $0.4490 | 86.4% | 0.1% | ||
| $0.0435 | $0.4996 | 88.8% | 2.4% | ||
| $0.0440 | $0.3048 | 66.4% | 3.1% | ||
| $0.0448 | $0.2390 | 86.5% | 2.8% | ||
| $0.0449 | $0.3991 | 78.7% | 0.3% | ||
| $0.0453 | $0.3743 | 81.4% | 4.2% | ||
| $0.0455 | $0.4996 | 87.1% | 10.2% | ||
| $0.0473 | $0.4997 | 85.6% | 1.7% | ||
| $0.0479 | $0.4996 | 90.1% | 7.8% | ||
| $0.0480 | $0.2942 | 57.2% | 0.2% | ||
| $0.0488 | $0.2991 | 79.1% | 0.7% | ||
| $0.0500 | $0.4996 | 83.4% | 6.5% | ||
| $0.0502 | $0.4996 | 83.1% | 1.2% | ||
| $0.0511 | $0.1646 | 76.2% | 0.6% | ||
| $0.0518 | $0.4998 | 81.8% | 0.1% | ||
| $0.0529 | $0.4997 | 80.9% | 1.4% | ||
| $0.0530 | $0.4996 | 80.8% | 0.5% | ||
| $0.0588 | $0.2497 | 27.0% | 0.1% | ||
| $0.0606 | $0.4693 | 84.7% | 1.3% | ||
| $0.0614 | $0.4990 | 73.8% | 0.1% | ||
| $0.0642 | $0.2392 | 70.4% | 0.4% | ||
| $0.0643 | $0.4996 | 71.4% | 0.1% | ||
| $0.0670 | $0.4997 | 69.2% | 1.7% | ||
| $0.0711 | $0.4998 | 65.8% | 5.0% | ||
| $0.0746 | $0.4993 | 62.8% | 0.0% | ||
| $0.0768 | $0.6239 | 64.3% | 0.0% | ||
| $0.0774 | $0.7492 | 82.0% | 1.6% | ||
| $0.0904 | $0.4996 | 49.6% | 0.3% | ||
Fast | $0.0934 | $0.6246 | 62.7% | 0.2% | |
| $0.1148 | $0.6244 | 39.5% | 0.0% |
- Effective in $0.0268 / Effective out $0.4995Token share2.0%
- Effective in $0.0269 / Effective out $0.3204Token share3.6%
- Effective in $0.0277 / Effective out $0.2498Token share0.5%
- Effective in $0.0310 / Effective out $0.0778Token share7.3%
- Effective in $0.0348 / Effective out $0.2997Token share5.5%
- Effective in $0.0358 / Effective out $0.3796Token share4.4%
- Effective in $0.0366 / Effective out $0.4996Token share1.6%
- Effective in $0.0379 / Effective out $0.1786Token share0.0%
- Effective in $0.0402 / Effective out $0.3491Token share6.1%
- Effective in $0.0412 / Effective out $0.1833Token share3.6%
- Effective in $0.0418 / Effective out $0.3493Token share2.0%
- Effective in $0.0418 / Effective out $0.4997Token share8.8%
- Effective in $0.0422 / Effective out $0.4490Token share0.1%
- Effective in $0.0435 / Effective out $0.4996Token share2.4%
- Effective in $0.0440 / Effective out $0.3048Token share3.1%
- Effective in $0.0448 / Effective out $0.2390Token share2.8%
- Effective in $0.0449 / Effective out $0.3991Token share0.3%
- Effective in $0.0453 / Effective out $0.3743Token share4.2%
- Effective in $0.0455 / Effective out $0.4996Token share10.2%
- Effective in $0.0473 / Effective out $0.4997Token share1.7%
- Effective in $0.0479 / Effective out $0.4996Token share7.8%
- Effective in $0.0480 / Effective out $0.2942Token share0.2%
- Effective in $0.0488 / Effective out $0.2991Token share0.7%
- Effective in $0.0500 / Effective out $0.4996Token share6.5%
- Effective in $0.0502 / Effective out $0.4996Token share1.2%
- Effective in $0.0511 / Effective out $0.1646Token share0.6%
- Effective in $0.0518 / Effective out $0.4998Token share0.1%
- Effective in $0.0529 / Effective out $0.4997Token share1.4%
- Effective in $0.0530 / Effective out $0.4996Token share0.5%
- Effective in $0.0588 / Effective out $0.2497Token share0.1%
- Effective in $0.0606 / Effective out $0.4693Token share1.3%
- Effective in $0.0614 / Effective out $0.4990Token share0.1%
- Effective in $0.0642 / Effective out $0.2392Token share0.4%
- Effective in $0.0643 / Effective out $0.4996Token share0.1%
- Effective in $0.0670 / Effective out $0.4997Token share1.7%
- Effective in $0.0711 / Effective out $0.4998Token share5.0%
- Effective in $0.0746 / Effective out $0.4993Token share0.0%
- Effective in $0.0768 / Effective out $0.6239Token share0.0%
- Effective in $0.0774 / Effective out $0.7492Token share1.6%
- Effective in $0.0904 / Effective out $0.4996Token share0.3%
- Effective in $0.0934 / Effective out $0.6246FastToken share0.2%
- Effective in $0.1148 / Effective out $0.6244Token share0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
P50, best across providers
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | GLM-5.3-Flash Intelligence Index | 27.8 |
| Artificial Analysis | GLM-5.3-Flash Coding Index | 71.5 |
| Artificial Analysis | GLM-5.3-Flash Agentic Index | 50.9 |
| Artificial Analysis | GLM-5.3-Flash GPQA Diamond | 91.2% |
| Artificial Analysis | GLM-5.3-Flash HLE | 39.9% |
| Artificial Analysis | GLM-5.3-Flash AA-LCR | 80.0% |
| Artificial Analysis | GLM-5.3-Flash τ-Bench Banking | 47.2% |
| Artificial Analysis | GLM-5.3-Flash GDPval-AA | 57.4% |
| Artificial Analysis | GLM-5.3-Flash CritPt | 15.4% |
| Artificial Analysis | GLM-5.3-Flash SciCode | 51.6% |
| Artificial Analysis | GLM-5.3-Flash Terminal-Bench 4.0 | 32.8% |
| Artificial Analysis | GLM-5.3-Flash Terminal-Bench 2.1 | 84.3% |
| Artificial Analysis | GLM-5.3-Flash AA-Omniscience Accuracy | 28.2% |
| Artificial Analysis | GLM-5.3-Flash AA-Omniscience Non-Hallucination Rate | 61.7% |
| Design Arena | GLM-5.3-Flash Models Arena 3D Elo | 1293 |
| Design Arena | GLM-5.3-Flash Models Arena Asciiart Elo | 1256 |
| Design Arena | GLM-5.3-Flash Models Arena Code Categories Elo | 1267 |
| Design Arena | GLM-5.3-Flash Models Arena Data Visualization Elo | 1257 |
| Design Arena | GLM-5.3-Flash Models Arena Game Development Elo | 1266 |
| Design Arena | GLM-5.3-Flash Models Arena SVG Elo | 1270 |
| Design Arena | GLM-5.3-Flash Models Arena UI Component Elo | 1294 |
| Design Arena | GLM-5.3-Flash Models Arena Website Elo | 1257 |
| Vals AI | GLM 5.3 Flash Access to Justice Benchmark | 71.1% |
| Vals AI | GLM 5.3 Flash Code Migration v1.1 | 51.6% |
| Vals AI | GLM 5.3 Flash CyberBench v1.1 | 67.9% |
| Vals AI | GLM 5.3 Flash CyberOffense | 18.3% |
| Vals AI | GLM 5.3 Flash EMB v1.1 | 66.3% |
| Vals AI | GLM 5.3 Flash Finance Agent v2.1 | 60.6% |
| Vals AI | GLM 5.3 Flash Vals Finance Index | 55.8% |
| Vals AI | GLM 5.3 Flash GPQA Diamond | 86.4% |
| Vals AI | GLM 5.3 Flash HLAB-Vals-1.1 | 10.4% |
| Vals AI | GLM 5.3 Flash IOI | 52.5% |
| Vals AI | GLM 5.3 Flash LiveCodeBench | 80.5% |
| Vals AI | GLM 5.3 Flash LegalBench | 83.9% |
| Vals AI | GLM 5.3 Flash Vals Legal Index | 71.1% |
| Vals AI | GLM 5.3 Flash Legal Research Bench | 45.2% |
| Vals AI | GLM 5.3 Flash MedScribe | 88.9% |
| Vals AI | GLM 5.3 Flash MMLU Pro | 86.1% |
| Vals AI | GLM 5.3 Flash MMMU Pro | 86.0% |
| Vals AI | GLM 5.3 Flash ProgramBench | 0.0% |
| Vals AI | GLM 5.3 Flash ProofBench v1.1 | 21.0% |
| Vals AI | GLM 5.3 Flash SAGE | 89.3% |
| Vals AI | GLM 5.3 Flash SkillsBench | 40.2% |
| Vals AI | GLM 5.3 Flash SRE Bench | 0.8% |
| Vals AI | GLM 5.3 Flash SWE-bench | 92.0% |
| Vals AI | GLM 5.3 Flash Tax Agent Bench | 31.6% |
| Vals AI | GLM 5.3 Flash TaxEval v2 | 75.6% |
| Vals AI | GLM 5.3 Flash Terminal-Bench 4.0 | 37.4% |
| Vals AI | GLM 5.3 Flash Terminal-Bench-Science | 2.9% |
| Vals AI | GLM 5.3 Flash Vals Index | 50.9% |
| Vals AI | GLM 5.3 Flash Vibe Code Bench 1-100 | 16.0% |
| Vals AI | GLM 5.3 Flash Vibe Code Bench v1.1 | 30.8% |
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Available through EU in-region routing
Z.ai: GLM 5.3 Flash is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
- Providers in Europe
- Inceptron
- Prices in Europe
- Inceptron: $0.175/M tokens input, $0.47/M tokens output
- Base URL
https://eu.openrouter.ai/api/v1- Plan
- Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with Z.ai: GLM 5.3 Flash on OpenRouter.
Frequently asked questions
Yes, the stealth model Ox Alpha was revealed to be ZAI's new model, GLM-5.3 Flash.
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
The GLM 5.3 Flash documentation on OpenRouter includes the Open-Weight vs Closed-Weight Models: What's the Difference? blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
GLM 5.3 Flash costs $0.0399/M input tokens and $0.0784/M output tokens, with separate rates for Cache Read at $0.03/M tokens.
GLM 5.3 Flash has a 1,048,576 token context window. It supports up to 131,072 completion tokens.
Yes. GLM 5.3 Flash accepts tools for function calling on 36 of the 37 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.
GLM 5.3 Flash accepts text, images, and video as input and returns text.
GLM 5.3 Flash is served by 37 providers on OpenRouter: Relace, Wafer, Morph, Open Inference, Darkbloom, Tenstorrent, GMICloud, NEAR AI and 29 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
GLM 5.3 Flash was released on August 26, 2026.