Z.ai: GLM 5.3
z-ai/glm-5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.
Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.
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).
| $0.5600 | $1.8000 | $0.1000 | 0.67s | 107 tok/s | ||
| $0.0699 | $1.4000 | $0.0689 | 0.32s | 90 tok/s | ||
| $0.1790 | $1.4000 | $0.1780 | 0.28s | 88 tok/s | ||
| $0.6000 | $2.5000 | $0.1000 | 0.63s | 96 tok/s | ||
| $0.9100 | $2.8600 | $0.1690 | 0.55s | 96 tok/s | ||
| $0.7500 | $3.0000 | $0.1900 | 0.45s | 94 tok/s | ||
| $0.9800 | $3.0800 | $0.1820 | 0.48s | 89 tok/s | ||
| $0.0840 | $3.6000 | $0.0790 | 0.36s | 82 tok/s | ||
| $0.0840 | $3.6000 | $0.0790 | 0.34s | 79 tok/s | ||
| $1.0000 | $3.8500 | $0.1344 | 0.82s | 91 tok/s | ||
| $0.5000 | $3.5000 | $0.1000 | 0.86s | 78 tok/s | ||
| $1.5000 | $2.0000 | $0.2000 | 0.29s | 90 tok/s | ||
| $0.0703 | $4.3843 | $0.0703 | 1.37s | 80 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.57s | 101 tok/s | ||
10% off | $1.40$1.2600 | $4.40$3.9600 | $0.26$0.2340 | 0.39s | 88 tok/s | |
| $0.1900 | $4.4000 | $0.1900 | 1.49s | 95 tok/s | ||
50% off | $1.40$0.7000 | $4.40$2.2000 | $0.26$0.1300 | 2.16s | 76 tok/s | |
| $1.1900 | $3.7400 | $0.2380 | 1.08s | 78 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.61s | 147 tok/s | ||
| $0.7500 | $3.0000 | $0.1200 | 0.54s | 62 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.60s | 77 tok/s | ||
| $1.5400 | $4.8400 | $0.1540 | 0.86s | 124 tok/s | ||
Fast | $2.1000 | $6.6000 | $0.2600 | 0.80s | 127 tok/s | |
| $1.4000 | $4.4000 | $0.2600 | 0.39s | 93 tok/s | ||
| $1.4000 | $4.4000 | $0.1400 | 1.09s | 114 tok/s | ||
55% off | $1.40$0.6300 | $4.40$1.9800 | $0.26$0.1170 | 1.69s | 46 tok/s | |
| $1.4000 | $4.4000 | $0.1400 | 1.13s | 61 tok/s | ||
| $1.0300 | $4.8050 | $0.2080 | 0.55s | 62 tok/s | ||
| $1.4000 | $4.4000 | $0.1400 | 0.96s | 67 tok/s | ||
| $0.7000 | $2.2000 | $0.1300 | 1.83s | 42 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 1.42s | 56 tok/s | ||
Fast | $2.1000 | $6.6000 | $0.3900 | 1.20s | 140 tok/s | |
| $1.6800 | $5.2800 | $0.3120 | 2.09s | 88 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.73s | 73 tok/s | ||
Fast | $2.1000 | $6.6000 | $0.2100 | 0.53s | 152 tok/s | |
| $1.0500 | $4.2000 | $0.1680 | 0.79s | 43 tok/s | ||
| $1.4000 | $4.4000 | $0.2800 | 0.67s | 73 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 1.20s | 69 tok/s | ||
| $2.1000 | $6.6000 | $0.4000 | 0.20s | 135 tok/s | ||
20% off | $1.75$1.4000 | $5.50$4.4000 | $0.325$0.2600 | 0.60s | 125 tok/s | |
50% off | $2.80$1.4000 | $8.80$4.4000 | $0.14$0.0700 | 3.30s | 80 tok/s | |
| $1.4000 | $4.4000 | $0.2600 | 1.77s | 49 tok/s | ||
50% off | $1.40$0.7000 | $4.40$2.2000 | $0.26$0.1300 | 2.61s | 59 tok/s | |
Prime | $1.6800 | $5.2800 | $0.3360 | 1.03s | 85 tok/s | |
| $1.4000 | $4.4000 | $0.2600 | 0.66s | 62 tok/s | ||
| $2.1000 | $6.6000 | $0.2100 | 0.47s | 133 tok/s | ||
| $0.90$0.5625 | $4.00$2.5000 | $0.20$0.1250 | 2.89s | 25 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | -- | -- | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $0.72$0.4500 | $3.20$2.0000 | $0.16$0.1000 | 2.82s | 55 tok/s | ||
- Input $0.56 / Output $1.80107 tok/s100.00% uptime
- Input $0.0699 / Output $1.4090 tok/s100.00% uptime
- Input $0.179 / Output $1.4088 tok/s100.00% uptime
- Input $0.60 / Output $2.5096 tok/s100.00% uptime
- Input $0.91 / Output $2.8696 tok/s100.00% uptime
- Input $0.75 / Output $3.0094 tok/s98.33% uptime
Input $0.98 / Output $3.0889 tok/s99.55% uptime- Input $0.084 / Output $3.6082 tok/s100.00% uptime
- Input $0.084 / Output $3.6079 tok/s100.00% uptime
- Input $1.00 / Output $3.8591 tok/s99.90% uptime
Input $0.50 / Output $3.5078 tok/s99.77% uptime- Input $1.50 / Output $2.0090 tok/s99.97% uptime
- Input $0.0703 / Output $4.384380 tok/s99.89% uptime
- Input $1.40 / Output $4.40101 tok/s100.00% uptime
- Input $1.26 / Output $3.9610% off88 tok/s100.00% uptime
- Input $0.19 / Output $4.4095 tok/s100.00% uptime
- Input $0.70 / Output $2.2050% off76 tok/s99.86% uptime
- Input $1.19 / Output $3.7478 tok/s100.00% uptime
- Input $1.40 / Output $4.40147 tok/s99.87% uptime
- Input $0.75 / Output $3.0062 tok/s99.96% uptime
Input $1.40 / Output $4.4077 tok/s99.94% uptime
Input $1.54 / Output $4.84124 tok/s99.87% uptime- Input $2.10 / Output $6.60127 tok/s98.13% uptimeFast
- Input $1.40 / Output $4.4093 tok/s100.00% uptime
Input $1.40 / Output $4.40114 tok/s99.88% uptime- Input $0.63 / Output $1.9855% off46 tok/s100.00% uptime
- Input $1.40 / Output $4.4061 tok/s100.00% uptime
- Input $1.03 / Output $4.80562 tok/s100.00% uptime
- Input $1.40 / Output $4.4067 tok/s100.00% uptime
- Input $0.70 / Output $2.2042 tok/s99.92% uptime
- Input $1.40 / Output $4.4056 tok/s100.00% uptime
Input $2.10 / Output $6.60140 tok/s99.91% uptimeFast- Input $1.68 / Output $5.2888 tok/s99.74% uptime
- Input $1.40 / Output $4.4073 tok/s100.00% uptime
- Input $2.10 / Output $6.60152 tok/s100.00% uptimeFast
- Input $1.05 / Output $4.2043 tok/s100.00% uptime
- Input $1.40 / Output $4.4073 tok/s100.00% uptime
- Input $1.40 / Output $4.4069 tok/s96.19% uptime

Input $2.10 / Output $6.60135 tok/s100.00% uptime- Input $1.40 / Output $4.4020% off125 tok/s100.00% uptime
- Input $1.40 / Output $4.4050% off80 tok/s100.00% uptime
- Input $1.40 / Output $4.4049 tok/s100.00% uptime
- Input $0.70 / Output $2.2050% off59 tok/s100.00% uptime
- Input $1.68 / Output $5.2885 tok/s100.00% uptimePrime
- Input $1.40 / Output $4.4062 tok/s96.37% uptime
- Input $2.10 / Output $6.60133 tok/s100.00% uptimeFast
Input $0.5625 / Output $2.5038% off25 tok/s99.41% uptime- Input $1.40 / Output $4.40-- tok/s99.78% uptime
- Not used in Standard routing:Why these endpoints are not used
Input $0.45 / Output $2.0055 tok/s100.00% uptimeFlex+11 more label
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 — Price history
| $0.0690 | $1.40 | 90.5% | 20.0% | ||
| $0.0703 | $4.38 | 89.4% | 1.3% | ||
| $0.0794 | $3.60 | 92.8% | 5.0% | ||
| $0.0794 | $3.60 | 91.4% | 4.9% | ||
| $0.1388 | $1.80 | 91.6% | 13.1% | ||
| $0.1496 | $3.50 | 88.0% | 2.3% | ||
| $0.1648 | $2.50 | 87.0% | 4.5% | ||
| $0.1685 | $2.20 | 93.2% | 0.8% | ||
| $0.1767 | $3.00 | 91.0% | 0.2% | ||
| $0.1781 | $1.40 | 90.1% | 4.2% | ||
| $0.1804 | $2.20 | 91.2% | 0.7% | ||
| $0.1847 | $2.20 | 90.4% | 0.3% | ||
| $0.1876 | $2.54 | 87.5% | 1.6% | ||
| $0.1900 | $4.40 | 62.0% | 0.4% | ||
| $0.2043 | $1.98 | 83.0% | 2.0% | ||
| $0.2082 | $4.03 | 91.5% | 3.0% | ||
| $0.2255 | $4.40 | 93.2% | 0.2% | ||
| $0.2388 | $3.08 | 92.9% | 4.5% | ||
| $0.2506 | $2.86 | 89.0% | 2.7% | ||
| $0.2531 | $4.40 | 91.0% | 0.5% | ||
| $0.2612 | $3.74 | 97.6% | 3.8% | ||
| $0.2626 | $3.00 | 87.0% | 3.0% | ||
| $0.2907 | $3.60 | 86.5% | 0.4% | ||
| $0.2947 | $4.40 | 87.7% | 0.6% | ||
| $0.3267 | $4.40 | 94.1% | 8.8% | ||
| $0.3335 | $4.40 | 95.2% | 0.0% | ||
| $0.3513 | $4.40 | 92.0% | 0.4% | ||
| $0.3794 | $3.23 | 76.9% | 0.3% | ||
| $0.3848 | $4.40 | 89.0% | 2.0% | ||
| $0.3851 | $4.20 | 75.4% | 0.0% | ||
| $0.3856 | $4.40 | 76.3% | 0.1% | ||
| $0.4027 | $4.40 | 87.5% | 0.5% | ||
| $0.4140 | $4.84 | 81.2% | 0.2% | ||
Prime | $0.4215 | $5.28 | 93.6% | 0.6% | |
Fast | $0.4601 | $6.60 | 86.8% | 0.4% | |
Fast | $0.4630 | $6.60 | 89.0% | 0.8% | |
| $0.4851 | $4.40 | 80.3% | 1.4% | ||
| $0.5082 | $6.60 | 84.2% | 0.4% | ||
| $0.5092 | $3.96 | 73.2% | 0.2% | ||
Fast | $0.5125 | $6.60 | 92.8% | 2.5% | |
| $0.5301 | $4.40 | 76.4% | 0.2% | ||
| $0.5409 | $6.60 | 91.7% | 0.5% | ||
| $0.5446 | $4.40 | 75.0% | 0.0% | ||
| $0.5491 | $5.28 | 82.7% | 0.3% | ||
| $0.8517 | $4.40 | 48.1% | 0.0% | ||
| $0.9121 | $4.40 | 42.8% | 0.0% | ||
| $0.9754 | $4.40 | 37.2% | 0.0% | ||
| — | — | — | — | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $0.1669 | $2.00 | 80.9% | 0.0% | ||
- Effective in $0.0690 / Effective out $1.40Token share20.0%
- Effective in $0.0703 / Effective out $4.38Token share1.3%
- Effective in $0.0794 / Effective out $3.60Token share5.0%
- Effective in $0.0794 / Effective out $3.60Token share4.9%
- Effective in $0.1388 / Effective out $1.80Token share13.1%
- Effective in $0.1496 / Effective out $3.50Token share2.3%
- Effective in $0.1648 / Effective out $2.50Token share4.5%
- Effective in $0.1685 / Effective out $2.20Token share0.8%
- Effective in $0.1767 / Effective out $3.00Token share0.2%
- Effective in $0.1781 / Effective out $1.40Token share4.2%
- Effective in $0.1804 / Effective out $2.20Token share0.7%
- Effective in $0.1847 / Effective out $2.20Token share0.3%
- Effective in $0.1876 / Effective out $2.54Token share1.6%
- Effective in $0.1900 / Effective out $4.40Token share0.4%
- Effective in $0.2043 / Effective out $1.98Token share2.0%
- Effective in $0.2082 / Effective out $4.03Token share3.0%
- Effective in $0.2255 / Effective out $4.40Token share0.2%
- Effective in $0.2388 / Effective out $3.08Token share4.5%
- Effective in $0.2506 / Effective out $2.86Token share2.7%
- Effective in $0.2531 / Effective out $4.40Token share0.5%
- Effective in $0.2612 / Effective out $3.74Token share3.8%
- Effective in $0.2626 / Effective out $3.00Token share3.0%
- Effective in $0.2907 / Effective out $3.60Token share0.4%
- Effective in $0.2947 / Effective out $4.40Token share0.6%
- Effective in $0.3267 / Effective out $4.40Token share8.8%
- Effective in $0.3335 / Effective out $4.40Token share0.0%
- Effective in $0.3513 / Effective out $4.40Token share0.4%
- Effective in $0.3794 / Effective out $3.23Token share0.3%
- Effective in $0.3848 / Effective out $4.40Token share2.0%
- Effective in $0.3851 / Effective out $4.20Token share0.0%
- Effective in $0.3856 / Effective out $4.40Token share0.1%
- Effective in $0.4027 / Effective out $4.40Token share0.5%
- Effective in $0.4140 / Effective out $4.84Token share0.2%
- Effective in $0.4215 / Effective out $5.28PrimeToken share0.6%
- Effective in $0.4601 / Effective out $6.60FastToken share0.4%
- Effective in $0.4630 / Effective out $6.60FastToken share0.8%
- Effective in $0.4851 / Effective out $4.40Token share1.4%
- Effective in $0.5082 / Effective out $6.60FastToken share0.4%
- Effective in $0.5092 / Effective out $3.96Token share0.2%
- Effective in $0.5125 / Effective out $6.60FastToken share2.5%
- Effective in $0.5301 / Effective out $4.40Token share0.2%
- Effective in $0.5409 / Effective out $6.60Token share0.5%
- Effective in $0.5446 / Effective out $4.40Token share0.0%
- Effective in $0.5491 / Effective out $5.28Token share0.3%
- Effective in $0.8517 / Effective out $4.40Token share0.0%
- Effective in $0.9121 / Effective out $4.40Token share0.0%
- Effective in $0.9754 / Effective out $4.40Token share0.0%
- Effective in — / Effective out —Token share —
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.1669 / Effective out $2.00FlexToken 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 (Max) Intelligence Index | 31.7 |
| Artificial Analysis | GLM-5.3 (Max) GPQA Diamond | 91.7% |
| Artificial Analysis | GLM-5.3 (Max) HLE | 42.3% |
| Artificial Analysis | GLM-5.3 (Max) AA-LCR | 79.7% |
| Artificial Analysis | GLM-5.3 (Max) τ³-Banking | 50.3% |
| Artificial Analysis | GLM-5.3 (Max) GDPval-AA | 57.7% |
| Artificial Analysis | GLM-5.3 (Max) CritPt | 19.1% |
| Artificial Analysis | GLM-5.3 (Max) SciCode | 59.0% |
| Artificial Analysis | GLM-5.3 (Max) Terminal-Bench 4.0 | 41.9% |
| Artificial Analysis | GLM-5.3 (Max) Terminal-Bench 2.1 | 83.9% |
| Artificial Analysis | GLM-5.3 (Max) AA-Omniscience Accuracy | 32.3% |
| Artificial Analysis | GLM-5.3 (Max) AA-Omniscience Non-Hallucination Rate | 61.1% |
| Artificial Analysis | GLM-5.3 (Low) Intelligence Index | 23.1 |
| Artificial Analysis | GLM-5.3 (Low) HLE | 36.6% |
| Artificial Analysis | GLM-5.3 (Low) AA-LCR | 72.7% |
| Artificial Analysis | GLM-5.3 (Low) GDPval-AA | 41.6% |
| Artificial Analysis | GLM-5.3 (Low) CritPt | 14.6% |
| Artificial Analysis | GLM-5.3 (Low) SciCode | 42.0% |
| Artificial Analysis | GLM-5.3 (Low) Terminal-Bench 4.0 | 34.8% |
| Artificial Analysis | GLM-5.3 (Low) AA-Omniscience Accuracy | 31.9% |
| Artificial Analysis | GLM-5.3 (Low) AA-Omniscience Non-Hallucination Rate | 36.8% |
| Design Arena | GLM-5.3 Models Arena 3D Elo | 1293 |
| Design Arena | GLM-5.3 Models Arena Asciiart Elo | 1184 |
| Design Arena | GLM-5.3 Models Arena Code Categories Elo | 1282 |
| Design Arena | GLM-5.3 Models Arena Data Visualization Elo | 1251 |
| Design Arena | GLM-5.3 Models Arena Game Development Elo | 1287 |
| Design Arena | GLM-5.3 Models Arena SVG Elo | 1244 |
| Design Arena | GLM-5.3 Models Arena UI Component Elo | 1283 |
| Design Arena | GLM-5.3 Models Arena Website Elo | 1278 |
| Design Arena | GLM-5.3 Agents Arena Htmlslides Elo | 1189 |
| Design Arena | GLM-5.3 Agents Arena Mobile Apps Elo | 1184 |
| Design Arena | GLM-5.3 Agents Arena Python-Pptxslides Elo | 1217 |
| Design Arena | GLM-5.3 Agents Arena Webapps Elo | 1270 |
| Vals AI | GLM 5.3 Access to Justice Benchmark | 73.7% |
| Vals AI | GLM 5.3 Code Migration v1.1 | 55.1% |
| Vals AI | GLM 5.3 CyberBench v1.1 | 72.1% |
| Vals AI | GLM 5.3 EMB v1.1 | 69.1% |
| Vals AI | GLM 5.3 Finance Agent v2.1 | 65.0% |
| Vals AI | GLM 5.3 Vals Finance Index | 61.4% |
| Vals AI | GLM 5.3 Financial Coaching Bench | 74.1% |
| Vals AI | GLM 5.3 GPQA Diamond | 88.1% |
| Vals AI | GLM 5.3 HLAB-Vals-1.1 | 14.6% |
| Vals AI | GLM 5.3 Immigration | 66.7% |
| Vals AI | GLM 5.3 IOI | 68.4% |
| Vals AI | GLM 5.3 LiveCodeBench | 80.5% |
| Vals AI | GLM 5.3 LegalBench | 84.8% |
| Vals AI | GLM 5.3 Vals Legal Index | 74.6% |
| Vals AI | GLM 5.3 Legal Research Bench | 49.0% |
| Vals AI | GLM 5.3 MedCode | 42.9% |
| Vals AI | GLM 5.3 MedScribe | 88.8% |
| Vals AI | GLM 5.3 MMLU Pro | 86.8% |
| Vals AI | GLM 5.3 MysteryMechanism | 23.0% |
| Vals AI | GLM 5.3 ProgramBench | 1.5% |
| Vals AI | GLM 5.3 ProofBench v1.1 | 49.0% |
| Vals AI | GLM 5.3 Public Benefits Bench v1.1 | 68.5% |
| Vals AI | GLM 5.3 Vals RSI Index | 22.9% |
| Vals AI | GLM 5.3 SkillsBench | 47.5% |
| Vals AI | GLM 5.3 SRE Bench | 9.2% |
| Vals AI | GLM 5.3 SWE-bench | 95.4% |
| Vals AI | GLM 5.3 Tax Agent Bench | 43.3% |
| Vals AI | GLM 5.3 TaxEval v2 | 72.4% |
| Vals AI | GLM 5.3 Terminal-Bench 4.0 | 38.9% |
| Vals AI | GLM 5.3 Terminal-Bench-Science | 5.7% |
| Vals AI | GLM 5.3 Vals Index | 59.8% |
| Vals AI | GLM 5.3 Vibe Code Bench 1-100 v1.1 | 29.8% |
| Vals AI | GLM 5.3 Vibe Code Bench v1.1 | 78.1% |
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 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, Mistral
- Prices in Europe
- Inceptron: $1/M tokens input, $3.85/M tokens output
- Mistral: $1.54/M tokens input, $4.84/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 on OpenRouter.
Frequently asked questions
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency. Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.
The GLM 5.3 documentation on OpenRouter includes the Self-Hosted LLM vs API: When Does Self-Hosting Pay Off blog post and the How to Benchmark LLMs blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
GLM 5.3 costs $0.0699/M input tokens and $1.40/M output tokens, with separate rates for Cache Read at $0.0689/M tokens.
GLM 5.3 has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.
Yes. GLM 5.3 accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.
GLM 5.3 is served by 37 providers on OpenRouter: Wafer, Relace, inference.net, AkashML, DeepInfra, Cohere, Decart, Tenstorrent 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 was released on August 18, 2026.